Search results for Long Short Term Memory Network

Found 194 documents, 5930 searched:

• A Brief History of the Neural Networks

  From the biological neuron to LLMs: How AI became smart.

  https://www.kdnuggets.com/a-brief-history-of-the-neural-networks

• Exploring Neural Networks

  Unlocking the power of AI: a suide to neural networks and their applications.

  https://www.kdnuggets.com/exploring-neural-networks

• Deep Learning Key Terms, Explained

  Gain a beginner's perspective on artificial neural networks and deep learning with this set of 14 straight-to-the-point related key concept definitions.

  https://www.kdnuggets.com/2016/10/deep-learning-key-terms-explained.html

• Classifying Long Text Documents Using BERT

  Transformer based language models such as BERT are really good at understanding the semantic context because they were designed specifically for that purpose. BERT outperforms all NLP baselines, but as we say in the scientific community, “no free lunch”. How can we use BERT to classify long text documents?

  https://www.kdnuggets.com/2022/02/classifying-long-text-documents-bert.html

• Learn Deep Learning by Building 15 Neural Network Projects in 2022

  Here are 15 neural network projects you can take on in 2022 to build your skills, your know-how, and your portfolio.

  https://www.kdnuggets.com/2022/01/15-neural-network-projects-build-2022.html

• How Much Memory is your Machine Learning Code Consuming?

  Learn how to quickly check the memory footprint of your machine learning function/module with one line of command. Generate a nice report too.

  https://www.kdnuggets.com/2021/07/memory-machine-learning-code-consuming.html

• Optimization Algorithms in Neural Networks">Optimization Algorithms in Neural Networks

  This article presents an overview of some of the most used optimizers while training a neural network.

  https://www.kdnuggets.com/2020/12/optimization-algorithms-neural-networks.html

• A Friendly Introduction to Graph Neural Networks

  Despite being what can be a confusing topic, graph neural networks can be distilled into just a handful of simple concepts. Read on to find out more.

  https://www.kdnuggets.com/2020/11/friendly-introduction-graph-neural-networks.html

• Recurrent Neural Networks (RNN): Deep Learning for Sequential Data

  Recurrent Neural Networks can be used for a number of ways such as detecting the next word/letter, forecasting financial asset prices in a temporal space, action modeling in sports, music composition, image generation, and more.

  https://www.kdnuggets.com/2020/07/rnn-deep-learning-sequential-data.html

• Generating cooking recipes using TensorFlow and LSTM Recurrent Neural Network: A step-by-step guide

  A character-level LSTM (Long short-term memory) RNN (Recurrent Neural Network) is trained on ~100k recipes dataset using TensorFlow. The model suggested the recipes "Cream Soda with Onions", "Puff Pastry Strawberry Soup", "Zucchini flavor Tea", and "Salmon Mousse of Beef and Stilton Salad with Jalapenos". Yum!? Follow along this detailed guide with code to create your own recipe-generating chef.

  https://www.kdnuggets.com/2020/07/generating-cooking-recipes-using-tensorflow.html

• The Unreasonable Progress of Deep Neural Networks in Natural Language Processing (NLP)

  Natural language processing has made incredible advances through advanced techniques in deep learning. Learn about these powerful models, and find how close (or far away) these approaches are to human-level understanding.

  https://www.kdnuggets.com/2020/06/unreasonable-progress-deep-neural-networks-nlp.html

• 3 Reasons to Use Random Forest® Over a Neural Network: Comparing Machine Learning versus Deep Learning

  Both the random forest algorithm and Neural Networks are different techniques that learn differently but can be used in similar domains. Why would you use one over the other?

  https://www.kdnuggets.com/2020/04/3-reasons-random-forest-neural-network-comparison.html

• 20 AI, Data Science, Machine Learning Terms You Need to Know in 2020 (Part 2)">20 AI, Data Science, Machine Learning Terms You Need to Know in 2020 (Part 2)

  We explain important AI, ML, Data Science terms you should know in 2020, including Double Descent, Ethics in AI, Explainability (Explainable AI), Full Stack Data Science, Geospatial, GPT-2, NLG (Natural Language Generation), PyTorch, Reinforcement Learning, and Transformer Architecture.

  https://www.kdnuggets.com/2020/03/ai-data-science-machine-learning-key-terms-part2.html

• Microsoft Introduces Project Petridish to Find the Best Neural Network for Your Problem">Microsoft Introduces Project Petridish to Find the Best Neural Network for Your Problem

  The new algorithm takes a novel approach to neural architecture search.

  https://www.kdnuggets.com/2020/01/microsoft-introduces-project-petridish-best-neural-network.html

• Designing Your Neural Networks

  Check out this step-by-step walk through of some of the more confusing aspects of neural nets to guide you to making smart decisions about your neural network architecture.

  https://www.kdnuggets.com/2019/11/designing-neural-networks.html

• Introduction to Artificial Neural Networks

  In this article, we’ll try to cover everything related to Artificial Neural Networks or ANN.

  https://www.kdnuggets.com/2019/10/introduction-artificial-neural-networks.html

• Recreating Imagination: DeepMind Builds Neural Networks that Spontaneously Replay Past Experiences

  DeepMind researchers created a model to be able to replay past experiences in a way that simulate the mechanisms in the hippocampus.

  https://www.kdnuggets.com/2019/10/recreating-imagination-deepmind-builds-neural-networks-spontaneously-replay-past-experiences.html

• Nothing but NumPy: Understanding & Creating Neural Networks with Computational Graphs from Scratch">Nothing but NumPy: Understanding & Creating Neural Networks with Computational Graphs from Scratch

  Entirely implemented with NumPy, this extensive tutorial provides a detailed review of neural networks followed by guided code for creating one from scratch with computational graphs.

  https://www.kdnuggets.com/2019/08/numpy-neural-networks-computational-graphs.html

• Neural Code Search: How Facebook Uses Neural Networks to Help Developers Search for Code Snippets

  Developers are always searching for answers to questions about their code. But how do they ask the right questions? Facebook is creating new NLP neural networks to help search code repositories that may advance information retrieval algorithms.

  https://www.kdnuggets.com/2019/07/neural-code-facebook-uses-neural-networks.html

• Training a Neural Network to Write Like Lovecraft">Training a Neural Network to Write Like Lovecraft

  In this post, the author attempts to train a neural network to generate Lovecraft-esque prose, known to be awkward and irregular at best. Did it end in success? If not, any suggestions on how it might have? Read on to find out.

  https://www.kdnuggets.com/2019/07/training-neural-network-write-like-lovecraft.html

• XGBoost Algorithm: Long May She Reign

  In recent years, XGBoost algorithm has gained enormous popularity in academic as well as business world. We outline some of the reasons behind this incredible success.

  https://www.kdnuggets.com/2019/05/xgboost-algorithm.html

• Using a Keras Long Short-Term Memory (LSTM) Model to Predict Stock Prices

  LSTMs are very powerful in sequence prediction problems because they’re able to store past information. This is important in our case because the previous price of a stock is crucial in predicting its future price.

  https://www.kdnuggets.com/2018/11/keras-long-short-term-memory-lstm-model-predict-stock-prices.html

• Sequence Modeling with Neural Networks – Part I

  In the context of this post, we will focus on modeling sequences as a well-known data structure and will study its specific learning framework.

  https://www.kdnuggets.com/2018/10/sequence-modeling-neural-networks-part-1.html

• The 8 Neural Network Architectures Machine Learning Researchers Need to Learn">The 8 Neural Network Architectures Machine Learning Researchers Need to Learn

  In this blog post, I want to share the 8 neural network architectures from the course that I believe any machine learning researchers should be familiar with to advance their work.

  https://www.kdnuggets.com/2018/02/8-neural-network-architectures-machine-learning-researchers-need-learn.html

• Using Genetic Algorithm for Optimizing Recurrent Neural Networks

  In this tutorial, we will see how to apply a Genetic Algorithm (GA) for finding an optimal window size and a number of units in Long Short-Term Memory (LSTM) based Recurrent Neural Network (RNN).

  https://www.kdnuggets.com/2018/01/genetic-algorithm-optimizing-recurrent-neural-network.html

• Exploring Recurrent Neural Networks

  We explore recurrent neural networks, starting with the basics, using a motivating weather modeling problem, and implement and train an RNN in TensorFlow.

  https://www.kdnuggets.com/2017/12/exploring-recurrent-neural-networks.html

• Understanding Deep Convolutional Neural Networks with a practical use-case in Tensorflow and Keras">Understanding Deep Convolutional Neural Networks with a practical use-case in Tensorflow and Keras

  We show how to build a deep neural network that classifies images to many categories with an accuracy of a 90%. This was a very hard problem before the rise of deep networks and especially Convolutional Neural Networks.

  https://www.kdnuggets.com/2017/11/understanding-deep-convolutional-neural-networks-tensorflow-keras.html

• 7 Types of Artificial Neural Networks for Natural Language Processing">7 Types of Artificial Neural Networks for Natural Language Processing

  What is an artificial neural network? How does it work? What types of artificial neural networks exist? How are different types of artificial neural networks used in natural language processing? We will discuss all these questions in the following article.

  https://www.kdnuggets.com/2017/10/7-types-artificial-neural-networks-natural-language-processing.html

• A Guide For Time Series Prediction Using Recurrent Neural Networks (LSTMs)

  Looking at the strengths of a neural network, especially a recurrent neural network, I came up with the idea of predicting the exchange rate between the USD and the INR.

  https://www.kdnuggets.com/2017/10/guide-time-series-prediction-recurrent-neural-networks-lstms.html

• Going deeper with recurrent networks: Sequence to Bag of Words Model

  Deep learning makes it possible to convert unstructured text to computable formats, incorporating semantic knowledge to train machine learning models. These digital data troves help us understand people on a new level.

  https://www.kdnuggets.com/2017/08/deeper-recurrent-networks-sequence-bag-words-model.html

• Building, Training, and Improving on Existing Recurrent Neural Networks

  In this post, we’ll provide a short tutorial for training a RNN for speech recognition, including code snippets throughout.

  https://www.kdnuggets.com/2017/05/building-training-improving-existing-recurrent-neural-networks.html

• How to Build a Recurrent Neural Network in TensorFlow

  This is a no-nonsense overview of implementing a recurrent neural network (RNN) in TensorFlow. Both theory and practice are covered concisely, and the end result is running TensorFlow RNN code.

  https://www.kdnuggets.com/2017/04/build-recurrent-neural-network-tensorflow.html

• Attention and Memory in Deep Learning and NLP

  An overview of attention mechanisms and memory in deep neural networks and why they work, including some specific applications in natural language processing and beyond.

  https://www.kdnuggets.com/2016/01/attention-memory-deep-learning-nlp.html

• MetaMind Mastermind Richard Socher: Uncut Interview

  In a wide-ranging interview, Richard Socher opens up about MetaMind, deep learning, the nature of corporate research, and the future of machine learning.

  https://www.kdnuggets.com/2015/10/metamind-mastermind-richard-socher-deep-learning-interview.html

• Recurrent Neural Networks Tutorial, Introduction

  Recurrent Neural Networks (RNNs) are popular models that have shown great promise in NLP and many other Machine Learning tasks. Here is a much-needed guide to key RNN models and a few brilliant research papers.

  https://www.kdnuggets.com/2015/10/recurrent-neural-networks-tutorial.html

• Data Science, Statistics and Machine Learning Dictionary

  Check out this curated list of the most used data science terminology and get a leg up on your learning.

  https://www.kdnuggets.com/2022/05/data-science-statistics-machine-learning-dictionary.html

• 8 AI/Machine Learning Projects To Make Your Portfolio Stand Out">8 AI/Machine Learning Projects To Make Your Portfolio Stand Out

  If you are just starting down a path toward a career in Data Science, or you are already a seasoned practitioner, then keeping active to advance your experience through side projects is invaluable to take you to the next professional level. These eight interesting project ideas with source code and reference articles will jump start you to thinking outside of the box.

  https://www.kdnuggets.com/2020/09/8-ml-ai-projects-stand-out.html

• Deep Learning for NLP: ANNs, RNNs and LSTMs explained!">Deep Learning for NLP: ANNs, RNNs and LSTMs explained!

  Learn about Artificial Neural Networks, Deep Learning, Recurrent Neural Networks and LSTMs like never before and use NLP to build a Chatbot!

  https://www.kdnuggets.com/2019/08/deep-learning-nlp-explained.html

• Using Deep Learning to Solve Real World Problems">Using Deep Learning to Solve Real World Problems

  Do you assume that deep learning is only being used for toy problems and in self-learning scenarios? This post includes several firsthand accounts of organizations using deep neural networks to solve real world problems.

  https://www.kdnuggets.com/2017/12/using-deep-learning-solve-real-world-problems.html

• 7 Steps to Understanding Deep Learning

  There are many deep learning resources freely available online, but it can be confusing knowing where to begin. Go from vague understanding of deep neural networks to knowledgeable practitioner in 7 steps!

  https://www.kdnuggets.com/2016/01/seven-steps-deep-learning.html

• Evaluating Methods for Calculating Document Similarity

  The blog covers methods for representing documents as vectors and computing similarity, such as Jaccard similarity, Euclidean distance, cosine similarity, and cosine similarity with TF-IDF, along with pre-processing steps for text data, such as tokenization, lowercasing, removing punctuation, removing stop words, and lemmatization.

  https://www.kdnuggets.com/evaluating-methods-for-calculating-document-similarity

• Top 10 Kaggle Machine Learning Projects to Become Data Scientist in 2024

  Master Data Science with Top 10 Kaggle ML Projects to become a Data Scientist.

  https://www.kdnuggets.com/top-10-kaggle-machine-learning-projects-to-become-data-scientist-in-2024

• Tackle computer science problems using both fundamental and modern algorithms in machine learning

  Master algorithms, including deep learning like LSTMs, GRUs, RNNs, and Generative AI & LLMs such as ChatGPT, with Packt's 50 Algorithms Every Programmer Should Know.

  https://www.kdnuggets.com/2023/11/packt-tackle-computer-science-problems-fundamental-modern-algorithms-machine-learning

• Comparing Natural Language Processing Techniques: RNNs, Transformers, BERT

  RNN, Transformers, and BERT are popular NLP techniques with tradeoffs in sequence modeling, parallelization, and pre-training for downstream tasks.

  https://www.kdnuggets.com/comparing-natural-language-processing-techniques-rnns-transformers-bert

• 7 Steps to Mastering Natural Language Processing

  Want to learn all about Natural Language Processing (NLP)? Here is a 7 step guide to help you go from the fundamentals of machine learning and Python to Transformers, recent advances in NLP, and beyond.

  https://www.kdnuggets.com/7-steps-to-mastering-natural-language-processing

• 30 Years of Data Science: A Review From a Data Science Practitioner

  A review from a data science practitioner.

  https://www.kdnuggets.com/30-years-of-data-science-a-review-from-a-data-science-practitioner

• 5 Portfolio Projects for Final Year Data Science Students

  From cleaning data to wowing recruiters - this blog shares 5 killer data science projects to launch your data science career and get hired!

  https://www.kdnuggets.com/5-portfolio-projects-for-final-year-data-science-students

• Ten Years of AI in Review

  From image classification to chatbot therapy.

  https://www.kdnuggets.com/2023/06/ten-years-ai-review.html

• AgentGPT: Autonomous AI Agents in your Browser

  Give your AI agent a name and goal, and watch it accomplish the assigned objective.

  https://www.kdnuggets.com/2023/06/agentgpt-autonomous-ai-agents-browser.html

• What Is ChatGPT Doing and Why Does It Work?

  In this article, we will explain how ChatGPT works and why it is able to produce coherent and diverse conversations.

  https://www.kdnuggets.com/2023/04/chatgpt-work.html

• DataLang: A New Programming Language for Data Scientists… Created by ChatGPT?

  I recently tasked ChatGPT-4's to come up with a new programming language appropriate for data scientists in their day to day tasks. Let's look at the results, and the process of getting there.

  https://www.kdnuggets.com/2023/04/datalang-new-programming-language-data-scientists-chatgpt.html

• First Open Source Implementation of DeepMind’s AlphaTensor

  The first open-source implementation of AlphaTensor has been released and opens the door for new developments to revolutionize the computational performance of deep learning models.

  https://www.kdnuggets.com/2023/03/first-open-source-implementation-deepmind-alphatensor.html

• 7 Best Libraries for Machine Learning Explained

  Learn about machine learning libraries for building and deploying machine learning models.

  https://www.kdnuggets.com/2023/01/7-best-libraries-machine-learning-explained.html

• Key Data Science, Machine Learning, AI and Analytics Developments of 2022

  It's the end of the year, and so it's time for KDnuggets to assemble a team of experts and get to the bottom of what the most important data science, machine learning, AI and analytics developments of 2022 were.

  https://www.kdnuggets.com/2022/12/key-data-science-machine-learning-ai-analytics-developments-2022.html

• The ABCs of NLP, From A to Z

  There is no shortage of tools today that can help you through the steps of natural language processing, but if you want to get a handle on the basics this is a good place to start. Read about the ABCs of NLP, all the way from A to Z.

  https://www.kdnuggets.com/2022/10/abcs-nlp-a-to-z.html

• Data Representation for Natural Language Processing Tasks

  In NLP we must find a way to represent our data (a series of texts) to our systems (e.g. a text classifier). As Yoav Goldberg asks, "How can we encode such categorical data in a way which is amenable for us by a statistical classifier?" Enter the word vector.

  https://www.kdnuggets.com/2018/11/data-representation-natural-language-processing.html

• 8 Innovative BERT Knowledge Distillation Papers That Have Changed The Landscape of NLP

  All of the papers present a particular point of view of findings in the BERT utilization.

  https://www.kdnuggets.com/2022/09/eight-innovative-bert-knowledge-distillation-papers-changed-nlp-landscape.html

• Machine Learning Is Not Like Your Brain Part 6: The Importance of Precise Synapse Weights and the Ability to Set Them Quickly

  In Part Six, I’ll show how limitations in synapses are even more of a problem. Precise synapse weights and the ability to set them quickly to a specific value are crucial to ML and biological neurons offer neither.

  https://www.kdnuggets.com/2022/08/machine-learning-like-brain-part-6-importance-precise-synapse-weights-ability-set-quickly.html

• Sentiment Analysis with KNIME

  Check out this tutorial on how to approach sentiment classification with supervised machine learning algorithms.

  https://www.kdnuggets.com/2021/11/sentiment-analysis-knime.html

• The Evolution of Tokenization – Byte Pair Encoding in NLP

  Though we have SOTA algorithms for tokenization, it's always a good practice to understand the evolution trail and learning how have we reached here. Read this introduction to Byte Pair Encoding.

  https://www.kdnuggets.com/2021/10/evolution-tokenization-byte-pair-encoding-nlp.html

• Surpassing Trillion Parameters and GPT-3 with Switch Transformers – a path to AGI?">Surpassing Trillion Parameters and GPT-3 with Switch Transformers – a path to AGI?

  Ever larger models churning on increasingly faster machines suggest a potential path toward smarter AI, such as with the massive GPT-3 language model. However, new, more lean, approaches are being conceived and explored that may rival these super-models, which could lead to a future with more efficient implementations of advanced AI-driven systems.

  https://www.kdnuggets.com/2021/10/trillion-parameters-gpt-3-switch-transformers-path-agi.html

• Writing Your First Distributed Python Application with Ray

  Using Ray, you can take Python code that runs sequentially and transform it into a distributed application with minimal code changes. Read on to find out why you should use Ray, and how to get started.

  https://www.kdnuggets.com/2021/08/distributed-python-application-ray.html

• Facebook Open Sources a Chatbot That Can Discuss Any Topic

  The new version expands the capabilities of its predecessor building a much more natural conversational experience.

  https://www.kdnuggets.com/2021/07/facebook-open-sources-chatbot-discuss-any-topic.html

• High-Performance Deep Learning: How to train smaller, faster, and better models – Part 5

  Training efficient deep learning models with any software tool is nothing without an infrastructure of robust and performant compute power. Here, current software and hardware ecosystems are reviewed that you might consider in your development when the highest performance possible is needed.

  https://www.kdnuggets.com/2021/07/high-performance-deep-learning-part5.html

• How to Use NVIDIA GPU Accelerated Libraries

  If you are wondering how you can take advantage of NVIDIA GPU accelerated libraries for your AI projects, this guide will help answer questions and get you started on the right path.

  https://www.kdnuggets.com/2021/07/nvidia-gpu-accelerated-libraries.html

• High Performance Deep Learning, Part 1

  Advancing deep learning techniques continue to demonstrate incredible potential to deliver exciting new AI-enhanced software and systems. But, training the most powerful models is expensive--financially, computationally, and environmentally. Increasing the efficiency of such models will have profound impacts in many ways, so developing future models with this intension in mind will only help to further expand the reach, applicability, and value of what deep learning has to offer.

  https://www.kdnuggets.com/2021/06/efficiency-deep-learning-part1.html

• Awesome list of datasets in 100+ categories

  With an estimated 44 zettabytes of data in existence in our digital world today and approximately 2.5 quintillion bytes of new data generated daily, there is a lot of data out there you could tap into for your data science projects. It's pretty hard to curate through such a massive universe of data, but this collection is a great start. Here, you can find data from cancer genomes to UFO reports, as well as years of air quality data to 200,000 jokes. Dive into this ocean of data to explore as you learn how to apply data science techniques or leverage your expertise to discover something new.

  https://www.kdnuggets.com/2021/05/awesome-list-datasets.html

• A checklist to track your Data Science progress">A checklist to track your Data Science progress

  Whether you are just starting out in data science or already a gainfully-employed professional, always learning more to advance through state-of-the-art techniques is part of the adventure. But, it can be challenging to track of your progress and keep an eye on what's next. Follow this checklist to help you scale your expertise from entry-level to advanced.

  https://www.kdnuggets.com/2021/05/checklist-data-science-progress.html

• Deep Learning Recommendation Models (DLRM): A Deep Dive

  The currency in the 21st century is no longer just data. It's the attention of people. This deep dive article presents the architecture and deployment issues experienced with the deep learning recommendation model, DLRM, which was open-sourced by Facebook in March 2019.

  https://www.kdnuggets.com/2021/04/deep-learning-recommendation-models-dlrm-deep-dive.html

• Deep Learning-based Real-time Video Processing

  In this article, we explore how to build a pipeline and process real-time video with Deep Learning to apply this approach to business use cases overviewed in our research.

  https://www.kdnuggets.com/2021/02/deep-learning-based-real-time-video-processing.html

• 2011: DanNet triggers deep CNN revolution

  In 2021, we are celebrating the 10-year anniversary of DanNet, which, in 2011, was the first pure deep convolutional neural network (CNN) to win computer vision contests. Read about its history here.

  https://www.kdnuggets.com/2021/02/dannet-triggers-deep-cnn-revolution.html

• Vision Transformers: Natural Language Processing (NLP) Increases Efficiency and Model Generality

  Why do we hear so little about transformer models applied to computer vision tasks? What about attention in computer vision networks?

  https://www.kdnuggets.com/2021/02/vision-transformers-nlp-efficiency-model-generality.html

• Machine learning adversarial attacks are a ticking time bomb

  Software developers and cyber security experts have long fought the good fight against vulnerabilities in code to defend against hackers. A new, subtle approach to maliciously targeting machine learning models has been a recent hot topic in research, but its statistical nature makes it difficult to find and patch these so-called adversarial attacks. Such threats in the real-world are becoming imminent as the adoption of machine learning spreads, and a systematic defense must be implemented.

  https://www.kdnuggets.com/2021/01/machine-learning-adversarial-attacks.html

• Machine learning is going real-time

  Extracting immediate predictions from machine learning algorithms on the spot based on brand-new data can offer a next level of interaction and potential value to its consumers. The infrastructure and tech stack required to implement such real-time systems is also next level, and many organizations -- especially in the US -- seem to be resisting. But, what even is real-time ML, and how can it deliver a better experience?

  https://www.kdnuggets.com/2021/01/machine-learning-real-time.html

• Popular Machine Learning Interview Questions, part 2

  Get ready for your next job interview requiring domain knowledge in machine learning with answers to these thirteen common questions.

  https://www.kdnuggets.com/2021/01/popular-machine-learning-interview-questions-part2.html

• 8 New Tools I Learned as a Data Scientist in 2020

  The author shares the data science tools learned while making the move from Docker to Live Deployments.

  https://www.kdnuggets.com/2021/01/8-new-tools-learned-data-scientist-2020.html

• Unsupervised Learning for Predictive Maintenance using Auto-Encoders

  This article outlines a machine learning approach to detect and diagnose anomalies in the context of machine maintenance, along with a number of introductory concepts, including: Introduction to machine maintenance; What is predictive maintenance?; ​​​​Approaches for machine diagnosis; Machine diagnosis using machine learning

  https://www.kdnuggets.com/2021/01/unsupervised-learning-predictive-maintenance-auto-encoders.html

• Microsoft and Google Open Sourced These Frameworks Based on Their Work Scaling Deep Learning Training

  Google and Microsoft have recently released new frameworks for distributed deep learning training.

  https://www.kdnuggets.com/2020/11/microsoft-google-open-sourced-frameworks-scaling-deep-learning-training.html

• How to Make Sense of the Reinforcement Learning Agents?

  In this blog post, you’ll learn what to keep track of to inspect/debug your agent learning trajectory. I’ll assume you are already familiar with the Reinforcement Learning (RL) agent-environment setting and you’ve heard about at least some of the most common RL algorithms and environments.

  https://www.kdnuggets.com/2020/10/make-sense-reinforcement-learning-agents.html

• Mastering Time Series Analysis with Help From the Experts

  Read this discussion with the “Time Series” Team at KNIME, answering such classic questions as "how much past is enough past?" others that any practitioner of time series analysis will find useful.

  https://www.kdnuggets.com/2020/10/mastering-time-series-analysis-experts.html

• An Introduction to AI, updated">An Introduction to AI, updated

  We provide an introduction to key concepts and methods in AI, covering Machine Learning and Deep Learning, with an updated extensive list that includes Narrow AI, Super Intelligence, and Classic Artificial Intelligence, as well as recent ideas of NeuroSymbolic AI, Neuroevolution, and Federated Learning.

  https://www.kdnuggets.com/2020/10/introduction-ai-updated.html

• Stop Running Jupyter Notebooks From Your Command Line

  Instead, run your Jupyter Notebook as a stand alone web app.

  https://www.kdnuggets.com/2020/10/stop-running-jupyter-notebooks-command-line.html

• Understanding Transformers, the Data Science Way

  Read this accessible and conversational article about understanding transformers, the data science way — by asking a lot of questions that is.

  https://www.kdnuggets.com/2020/10/understanding-transformers-data-science-way.html

• MathWorks Deep learning workflow: tips, tricks, and often forgotten steps

  Getting started in deep learning – and adopting an organized, sustainable, and reproducible workflow – can be challenging. This blog post will share some tips and tricks to help you develop a systematic, effective, attainable, and scalable deep learning workflow as you experiment with different deep learning models, datasets, and applications.

  https://www.kdnuggets.com/2020/09/mathworks-deep-learning-workflow.html

• Deep Learning’s Most Important Ideas">Deep Learning’s Most Important Ideas

  In the field of deep learning, there continues to be a deluge of research and new papers published daily. Many well-adopted ideas that have stood the test of time provide the foundation for much of this new work. To better understand modern deep learning, these techniques cover the basic necessary knowledge, especially as a starting point if you are new to the field.

  https://www.kdnuggets.com/2020/09/deep-learnings-most-important-ideas.html

• A Deep Dive Into the Transformer Architecture – The Development of Transformer Models

  Even though transformers for NLP were introduced only a few years ago, they have delivered major impacts to a variety of fields from reinforcement learning to chemistry. Now is the time to better understand the inner workings of transformer architectures to give you the intuition you need to effectively work with these powerful tools.

  https://www.kdnuggets.com/2020/08/transformer-architecture-development-transformer-models.html

• Containerization of PySpark Using Kubernetes

  This article demonstrates the approach of how to use Spark on Kubernetes. It also includes a brief comparison between various cluster managers available for Spark.

  https://www.kdnuggets.com/2020/08/containerization-pyspark-kubernetes.html

• Deep Learning for Signal Processing: What You Need to Know

  Signal Processing is a branch of electrical engineering that models and analyzes data representations of physical events. It is at the core of the digital world. And now, signal processing is starting to make some waves in deep learning.

  https://www.kdnuggets.com/2020/07/deep-learning-signal-processing.html

• Powerful CSV processing with kdb+

  This article provides a glimpse into the available tools to work with CSV files and describes how kdb+ and its query language q raise CSV processing to a new level of performance and simplicity.

  https://www.kdnuggets.com/2020/07/powerful-csv-processing-kdb.html

• PyTorch LSTM: Text Generation Tutorial

  Key element of LSTM is the ability to work with sequences and its gating mechanism.

  https://www.kdnuggets.com/2020/07/pytorch-lstm-text-generation-tutorial.html

• Deep Learning in Finance: Is This The Future of the Financial Industry?

  Get a handle on how deep learning is affecting the finance industry, and identify resources to further this understanding and increase your knowledge of the various aspects.

  https://www.kdnuggets.com/2020/07/deep-learning-finance-future-financial-industry.html

• Complex logic at breakneck speed: Try Julia for data science

  We show a comparative performance benchmarking of Julia with an equivalent Python code to show why Julia is great for data science and machine learning.

  https://www.kdnuggets.com/2020/05/complex-logic-breakneck-speed-julia-data-science.html

• 13 must-read papers from AI experts">13 must-read papers from AI experts

  What research articles do top AI experts in the field recommend? Find out which ones and why, then be sure to add each to your reading to do list.

  https://www.kdnuggets.com/2020/05/13-must-read-papers-ai-experts.html

• What You Need to Know About Deep Reinforcement Learning

  How does deep learning solve the challenges of scale and complexity in reinforcement learning? Learn how combining these approaches will make more progress toward the notion of Artificial General Intelligence.

  https://www.kdnuggets.com/2020/05/deep-reinforcement-learning.html

• LSTM for time series prediction

  Learn how to develop a LSTM neural network with PyTorch on trading data to predict future prices by mimicking actual values of the time series data.

  https://www.kdnuggets.com/2020/04/lstm-time-series-prediction.html

• Peer Reviewing Data Science Projects">Peer Reviewing Data Science Projects

  In any technical development field, having other practitioners review your work before shipping code off to production is a valuable support tool to make sure your work is error-proof. Even through your preparation for the review, improvements might be discovered and then other issues that escaped your awareness can be spotted by outsiders. This peer scrutiny can also be applied to Data Science, and this article outlines a process that you can experiment with in your team.

  https://www.kdnuggets.com/2020/04/peer-reviewing-data-science-projects.html

• DeepMind Unveils Agent57, the First AI Agents that Outperforms Human Benchmarks in 57 Atari Games

  The new reinforcement learning agent innovates over previous architectures achieving one of the most important milestones in the AI space.

  https://www.kdnuggets.com/2020/04/deepmind-agent57-atari-games.html

• Build an app to generate photorealistic faces using TensorFlow and Streamlit

  We’ll show you how to quickly build a Streamlit app to synthesize celebrity faces using GANs, Tensorflow, and st.cache.

  https://www.kdnuggets.com/2020/04/app-generate-photorealistic-faces-tensorflow-streamlit.html

• How (not) to use Machine Learning for time series forecasting: The sequel">How (not) to use Machine Learning for time series forecasting: The sequel

  Developing machine learning predictive models from time series data is an important skill in Data Science. While the time element in the data provides valuable information for your model, it can also lead you down a path that could fool you into something that isn't real. Follow this example to learn how to spot trouble in time series data before it's too late.

  https://www.kdnuggets.com/2020/03/machine-learning-time-series-forecasting-sequel.html

• Introduction to Kubeflow MPI Operator and Industry Adoption

  Kubeflow just announced its first major 1.0 release recently. This post introduces the MPI Operator, one of the core components of Kubeflow, currently in alpha, which makes it easy to run synchronized, allreduce-style distributed training on Kubernetes.

  https://www.kdnuggets.com/2020/03/introduction-kubeflow-mpi-operator-industry-adoption.html

• Deep Learning Breakthrough: a sub-linear deep learning algorithm that does not need a GPU?

  Deep Learning sits at the forefront of many important advances underway in machine learning. With backpropagation being a primary training method, its computational inefficiencies require sophisticated hardware, such as GPUs. Learn about this recent breakthrough algorithmic advancement with improvements to the backpropgation calculations on a CPU that outperforms large neural network training with a GPU.

  https://www.kdnuggets.com/2020/03/deep-learning-breakthrough-sub-linear-algorithm-no-gpu.html

• Can Edge Analytics Become a Game Changer?

  Edge analytics is considered to be the future of sensor handling, and this article discusses its benefits and architecture of modern edge devices, gateways, and sensors. Deep Learning for edge analytics is also considered along with a review of experiments in human and chess figure detection using edge devices.

  https://www.kdnuggets.com/2020/02/edge-analytics-game-changer.html

• Passive Data Collection and Actionable Results: What to Know

  There are plenty of ways to get actionable results by using passive data. However, such an outcome will not happen without careful forethought. Data analysts must consider several crucial specifics, including what questions they want and expect the information to answer, and how they'll apply the findings to aid the business.

  https://www.kdnuggets.com/2020/02/passive-data-collection-actionable-results.html

• Illustrating the Reformer

  In this post, we will try to dive into the Reformer model and try to understand it with some visual guides.

  https://www.kdnuggets.com/2020/02/illustrating-reformer.html

• Top 10 AI, Machine Learning Research Articles to know">Top 10 AI, Machine Learning Research Articles to know

  We’ve seen many predictions for what new advances are expected in the field of AI and machine learning. Here, we review a “data set” based on what researchers were apparently studying at the turn of the decade to take a fresh glimpse into what might come to pass in 2020.

  https://www.kdnuggets.com/2020/01/top-10-ai-ml-articles-to-know.html

• Graph Machine Learning Meets UX: An uncharted love affair

  When machine learning tools are developed by technology first, they risk failing to deliver on what users actually need. It can also be difficult for development teams to establish meaningful direction. This article explores the challenges of designing an interface that enables users to visualise and interact with insights from graph machine learning, and explores the very new, uncharted relationship between machine learning and UX.

  https://www.kdnuggets.com/2020/01/graph-machine-learning-ux.html

• A Comprehensive Guide to Natural Language Generation

  Follow this overview of Natural Language Generation covering its applications in theory and practice. The evolution of NLG architecture is also described from simple gap-filling to dynamic document creation along with a summary of the most popular NLG models.

  https://www.kdnuggets.com/2020/01/guide-natural-language-generation.html

• H2O Framework for Machine Learning

  This article is an overview of H2O, a scalable and fast open-source platform for machine learning. We will apply it to perform classification tasks.

  https://www.kdnuggets.com/2020/01/h2o-framework-machine-learning.html

• Automatic Text Summarization in a Nutshell

  Marketing scientist Kevin Gray asks Dr. Anna Farzindar of the University of Southern California about Automatic Text Summarization and the various ways it is used.

  https://www.kdnuggets.com/2019/12/automatic-text-summarization-nutshell.html

• NeurIPS 2019 Outstanding Paper Awards

  NeurIPS 2019 is underway in Vancouver, and the committee has just recently announced this year's Outstanding Paper Awards. Find out what the selections were, along with some additional info on NeurIPS papers, here.

  https://www.kdnuggets.com/2019/12/neurips-2019-paper-awards.html

• Enabling the Deep Learning Revolution

  Deep learning models are revolutionizing the business and technology world with jaw-dropping performances in one application area after another. Read this post on some of the numerous composite technologies which allow deep learning its complex nonlinearity.

  https://www.kdnuggets.com/2019/12/enabling-deep-learning-revolution.html

• Pro Tips: How to deal with Class Imbalance and Missing Labels

  Your spectacularly-performing machine learning model could be subject to the common culprits of class imbalance and missing labels. Learn how to handle these challenges with techniques that remain open areas of new research for addressing real-world machine learning problems.

  https://www.kdnuggets.com/2019/11/tips-class-imbalance-missing-labels.html

• Research Guide for Transformers

  The problem with RNNs and CNNs is that they aren’t able to keep up with context and content when sentences are too long. This limitation has been solved by paying attention to the word that is currently being operated on. This guide will focus on how this problem can be addressed by Transformers with the help of deep learning.

  https://www.kdnuggets.com/2019/10/research-guide-transformers.html

• Everything a Data Scientist Should Know About Data Management">Everything a Data Scientist Should Know About Data Management

  For full-stack data science mastery, you must understand data management along with all the bells and whistles of machine learning. This high-level overview is a road map for the history and current state of the expansive options for data storage and infrastructure solutions.

  https://www.kdnuggets.com/2019/10/data-scientist-data-management.html

• Beyond Word Embedding: Key Ideas in Document Embedding

  This literature review on document embedding techniques thoroughly covers the many ways practitioners develop rich vector representations of text -- from single sentences to entire books.

  https://www.kdnuggets.com/2019/10/beyond-word-embedding-document-embedding.html

• What is Hierarchical Clustering?

  The article contains a brief introduction to various concepts related to Hierarchical clustering algorithm.

  https://www.kdnuggets.com/2019/09/hierarchical-clustering.html

• A 2019 Guide for Automatic Speech Recognition

  In this article, we’ll look at a couple of papers aimed at solving the problem of automated speech recognition with machine and deep learning.

  https://www.kdnuggets.com/2019/09/2019-guide-automatic-speech-recognition.html

• A 2019 Guide to Speech Synthesis with Deep Learning

  In this article, we’ll look at research and model architectures that have been written and developed to do just that using deep learning.

  https://www.kdnuggets.com/2019/09/2019-guide-speech-synthesis-deep-learning.html

• TensorFlow vs PyTorch vs Keras for NLP">TensorFlow vs PyTorch vs Keras for NLP

  These three deep learning frameworks are your go-to tools for NLP, so which is the best? Check out this comparative analysis based on the needs of NLP, and find out where things are headed in the future.

  https://www.kdnuggets.com/2019/09/tensorflow-pytorch-keras-nlp.html

• Beyond Neurons: Five Cognitive Functions of the Human Brain that we are Trying to Recreate with Artificial Intelligence

  The quest for recreating cognitive capabilities of the brain in deep neural networks remains one of the elusive goals of AI. Let’s explore some human cognitive skills that are serving as inspiration to a new generation of AI techniques.

  https://www.kdnuggets.com/2019/09/beyond-neurons-five-cognitive-functions-human-brain-recreate-artificial-intelligence.html

• Deep Learning Next Step: Transformers and Attention Mechanism">Deep Learning Next Step: Transformers and Attention Mechanism

  With the pervasive importance of NLP in so many of today's applications of deep learning, find out how advanced translation techniques can be further enhanced by transformers and attention mechanisms.

  https://www.kdnuggets.com/2019/08/deep-learning-transformers-attention-mechanism.html

• Artificial Intelligence vs. Machine Learning vs. Deep Learning: What is the Difference?

  Over the past few years, artificial intelligence continues to be one of the hottest topics. And in order to work effectively with it, you need to understand its constituent parts.

  https://www.kdnuggets.com/2019/08/artificial-intelligence-vs-machine-learning-vs-deep-learning-difference.html

• Deep Learning for NLP: Creating a Chatbot with Keras!">Deep Learning for NLP: Creating a Chatbot with Keras!

  Learn how to use Keras to build a Recurrent Neural Network and create a Chatbot! Who doesn’t like a friendly-robotic personal assistant?

  https://www.kdnuggets.com/2019/08/deep-learning-nlp-creating-chatbot-keras.html

• Pytorch Cheat Sheet for Beginners and Udacity Deep Learning Nanodegree

  This cheatsheet should be easier to digest than the official documentation and should be a transitional tool to get students and beginners to get started reading documentations soon.

  https://www.kdnuggets.com/2019/08/pytorch-cheat-sheet-beginners.html

• Understanding Tensor Processing Units

  The Tensor Processing Unit (TPU) is Google's custom tool to accelerate machine learning workloads using the TensorFlow framework. Learn more about what TPUs do and how they can work for you.

  https://www.kdnuggets.com/2019/07/understanding-tensor-processing-units.html

• Top 13 Skills To Become a Rockstar Data Scientist">Top 13 Skills To Become a Rockstar Data Scientist

  Education, coding, SQL, big data platforms, storytelling and more. These are the 13 skills you need to master to become a rockstar data scientist.

  https://www.kdnuggets.com/2019/07/top-13-skills-become-rockstar-data-scientist.html

• A Summary of DeepMind’s Protein Folding Upset at CASP13">A Summary of DeepMind’s Protein Folding Upset at CASP13

  Learn how DeepMind dominated the last CASP competition for advancing protein folding models. Their approach using gradient descent is today's state of the art for predicting the 3D structure of a protein knowing only its comprising amino acid compounds.

  https://www.kdnuggets.com/2019/07/deepmind-protein-folding-upset.html

• Secrets to a Successful Data Science Interview

  Are you puzzled as to what to prepare for data science interviews? That you are reading this document is a reflection of your seriousness in being a successful data scientist.

  https://www.kdnuggets.com/2019/07/secrets-data-science-interview.html

• Collaborative Evolutionary Reinforcement Learning

  Intel Researchers created a new approach to RL via Collaborative Evolutionary Reinforcement Learning (CERL) that combines policy gradient and evolution methods to optimize, exploit, and explore challenges.

  https://www.kdnuggets.com/2019/07/collaborative-evolutionary-reinforcement-learning.html

• Understanding Cloud Data Services">Understanding Cloud Data Services

  Ready to move your systems to a cloud vendor or just learning more about big data services? This overview will help you understand big data system architectures, components, and offerings with an end-to-end taxonomy of what is available from the big three cloud providers.

  https://www.kdnuggets.com/2019/06/understanding-cloud-data-services.html