Search results for activation function
-
Improving the Performance of a Neural Network
There are many techniques available that could help us achieve that. Follow along to get to know them and to build your own accurate neural network.https://www.kdnuggets.com/2018/05/improving-performance-neural-network.html
-
Complete Guide to Build ConvNet HTTP-Based Application using TensorFlow and Flask RESTful Python API">Complete Guide to Build ConvNet HTTP-Based Application using TensorFlow and Flask RESTful Python API
In this tutorial, a CNN is to be built, and trained and tested against the CIFAR10 dataset. To make the model remotely accessible, a Flask Web application is created using Python to receive an uploaded image and return its classification label using HTTP.https://www.kdnuggets.com/2018/05/complete-guide-convnet-tensorflow-flask-restful-python-api.html
-
Detecting Breast Cancer with Deep Learning
Breast cancer is the most common invasive cancer in women, and the second main cause of cancer death in women, after lung cancer. In this article I will build a WideResNet based neural network to categorize slide images into two classes, one that contains breast cancer and other that doesn’t using Deep Learning Studio.https://www.kdnuggets.com/2018/05/detecting-breast-cancer-deep-learning.html
-
Building Convolutional Neural Network using NumPy from Scratch">Building Convolutional Neural Network using NumPy from Scratch
In this article, CNN is created using only NumPy library. Just three layers are created which are convolution (conv for short), ReLU, and max pooling.https://www.kdnuggets.com/2018/04/building-convolutional-neural-network-numpy-scratch.html
-
A “Weird” Introduction to Deep Learning">A “Weird” Introduction to Deep Learning
There are amazing introductions, courses and blog posts on Deep Learning. But this is a different kind of introduction.https://www.kdnuggets.com/2018/03/weird-introduction-deep-learning.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
-
Is Learning Rate Useful in Artificial Neural Networks?
This article will help you understand why we need the learning rate and whether it is useful or not for training an artificial neural network. Using a very simple Python code for a single layer perceptron, the learning rate value will get changed to catch its idea.https://www.kdnuggets.com/2018/01/learning-rate-useful-neural-network.html
-
Custom Optimizer in TensorFlow
How to customize the optimizers to speed-up and improve the process of finding a (local) minimum of the loss function using TensorFlow.https://www.kdnuggets.com/2018/01/custom-optimizer-tensorflow.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
-
Top 10 Videos on Deep Learning in Python">Top 10 Videos on Deep Learning in Python
Playlists, individual tutorials (not part of a playlist) and online courses on Deep Learning (DL) in Python using the Keras, Theano, TensorFlow and PyTorch libraries. Assumes no prior knowledge. These videos cover all skill levels and time constraints!https://www.kdnuggets.com/2017/11/top-10-videos-deep-learning-python.html
-
Want to know how Deep Learning works? Here’s a quick guide for everyone">Want to know how Deep Learning works? Here’s a quick guide for everyone
Once you’ve read this article, you will understand the basics of AI and ML. More importantly, you will understand how Deep Learning, the most popular type of ML, works.https://www.kdnuggets.com/2017/11/deep-learning-works-quick-guide-everyone.html
-
7 Steps to Mastering Deep Learning with Keras">7 Steps to Mastering Deep Learning with Keras
Are you interested in learning how to use Keras? Do you already have an understanding of how neural networks work? Check out this lean, fat-free 7 step plan for going from Keras newbie to master of its basics as quickly as is possible.https://www.kdnuggets.com/2017/10/seven-steps-deep-learning-keras.html
-
Neural Networks, Step 1: Where to Begin with Neural Nets & Deep Learning
This is a short post for beginners learning neural networks, covering several essential neural networks concepts.https://www.kdnuggets.com/2017/10/neural-networks-step-1.html
-
Neural Network Foundations, Explained: Updating Weights with Gradient Descent & Backpropagation
In neural networks, connection weights are adjusted in order to help reconcile the differences between the actual and predicted outcomes for subsequent forward passes. But how, exactly, do these weights get adjusted?https://www.kdnuggets.com/2017/10/neural-network-foundations-explained-gradient-descent.html
-
TensorFlow: Building Feed-Forward Neural Networks Step-by-Step">TensorFlow: Building Feed-Forward Neural Networks Step-by-Step
This article will take you through all steps required to build a simple feed-forward neural network in TensorFlow by explaining each step in details.https://www.kdnuggets.com/2017/10/tensorflow-building-feed-forward-neural-networks-step-by-step.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
-
Understanding Machine Learning Algorithms">Understanding Machine Learning Algorithms
Machine learning algorithms aren’t difficult to grasp if you understand the basic concepts. Here, a SAS data scientist describes the foundations for some of today’s popular algorithms.https://www.kdnuggets.com/2017/10/understanding-machine-learning-algorithms.html
-
Evaluating Data Science Projects: A Case Study Critique
It’s not necessary to understand the inner workings of a machine learning project, but you should understand whether the right things have been measured and whether the results are suited to the business problem. You need to know whether to believe what data scientists are telling you.https://www.kdnuggets.com/2017/09/evaluating-data-science-projects-case-study-critique.html
-
Keras Tutorial: Recognizing Tic-Tac-Toe Winners with Neural Networks
In this tutorial, we will build a neural network with Keras to determine whether or not tic-tac-toe games have been won by player X for given endgame board configurations. Introductory neural network concerns are covered.https://www.kdnuggets.com/2017/09/neural-networks-tic-tac-toe-keras.html
-
First Steps of Learning Deep Learning: Image Classification in Keras
Whether you want to start learning deep learning for you career, to have a nice adventure (e.g. with detecting huggable objects) or to get insight into machines before they take over, this post is for you!https://www.kdnuggets.com/2017/08/first-steps-learning-deep-learning-image-classification-keras.html
-
Mind Reading: Using Artificial Neural Nets to Predict Viewed Image Categories From EEG Readings
This post outlines the approach taken at a recent deep learning hackathon, hosted by YCombinator-backed startup DeepGram. The dataset: EEG readings from a Stanford research project that predicted which category of images their test subjects were viewing using linear discriminant analysis.https://www.kdnuggets.com/2017/08/mind-reading-using-artificial-neural-nets.html
-
Introduction to Neural Networks, Advantages and Applications">Introduction to Neural Networks, Advantages and Applications
Artificial Neural Network (ANN) algorithm mimic the human brain to process information. Here we explain how human brain and ANN works.https://www.kdnuggets.com/2017/07/introduction-neural-networks-advantages-applications.html
-
The Machine Learning Algorithms Used in Self-Driving Cars">The Machine Learning Algorithms Used in Self-Driving Cars
Machine Learning applications include evaluation of driver condition or driving scenario classification through data fusion from different external and internal sensors. We examine different algorithms used for self-driving cars.https://www.kdnuggets.com/2017/06/machine-learning-algorithms-used-self-driving-cars.html
-
The Practical Importance of Feature Selection">The Practical Importance of Feature Selection
Feature selection is useful on a variety of fronts: it is the best weapon against the Curse of Dimensionality; it can reduce overall training times; and it is a powerful defense against overfitting, increasing generalizability.https://www.kdnuggets.com/2017/06/practical-importance-feature-selection.html
-
Deep Learning: TensorFlow Programming via XML and PMML
In this approach, problem dataset and its Neural network are specified in a PMML like XML file. Then it is used to populate the TensorFlow graph, which, in turn run to get the results.https://www.kdnuggets.com/2017/06/deep-learning-tensorflow-programming-xml-pmml.html
-
5 Machine Learning Projects You Can No Longer Overlook, April">5 Machine Learning Projects You Can No Longer Overlook, April
It's about that time again... 5 more machine learning or machine learning-related projects you may not yet have heard of, but may want to consider checking out. Find tools for data exploration, topic modeling, high-level APIs, and feature selection herein.https://www.kdnuggets.com/2017/04/five-machine-learning-projects-cant-overlook-april.html
-
arXiv Paper Spotlight: Why Does Deep and Cheap Learning Work So Well?
The recent paper at hand approaches explaining deep learning from a different perspective, that of physics, and discusses the role of "cheap learning" (parameter reduction) and how it relates back to this innovative perspective.https://www.kdnuggets.com/2016/12/arxiv-spotlight-deep-cheap-learning.html
-
Artificial Neural Networks (ANN) Introduction, Part 1
This intro to ANNs will look at how we can train an algorithm to recognize images of handwritten digits. We will be using the images from the famous MNIST (Mixed National Institute of Standards and Technology) database.https://www.kdnuggets.com/2016/12/artificial-neural-networks-intro-part-1.html
-
Implementing a CNN for Human Activity Recognition in Tensorflow
In this post, we will see how to employ Convolutional Neural Network (CNN) for HAR, that will learn complex features automatically from the raw accelerometer signal to differentiate between different activities of daily life.https://www.kdnuggets.com/2016/11/implementing-cnn-human-activity-recognition-tensorflow.html
-
An Intuitive Explanation of Convolutional Neural Networks
This article provides a easy to understand introduction to what convolutional neural networks are and how they work.https://www.kdnuggets.com/2016/11/intuitive-explanation-convolutional-neural-networks.html
-
A Quick Introduction to Neural Networks
This article provides a beginner level introduction to multilayer perceptron and backpropagation.https://www.kdnuggets.com/2016/11/quick-introduction-neural-networks.html
-
A Beginner’s Guide to Neural Networks with Python and SciKit Learn 0.18!">A Beginner’s Guide to Neural Networks with Python and SciKit Learn 0.18!
This post outlines setting up a neural network in Python using Scikit-learn, the latest version of which now has built in support for Neural Network models.https://www.kdnuggets.com/2016/10/beginners-guide-neural-networks-python-scikit-learn.html
-
Artificial Intelligence, Deep Learning, and Neural Networks, Explained">Artificial Intelligence, Deep Learning, and Neural Networks, Explained
This article is meant to explain the concepts of AI, deep learning, and neural networks at a level that can be understood by most non-practitioners, and can also serve as a reference or review for technical folks as well.https://www.kdnuggets.com/2016/10/artificial-intelligence-deep-learning-neural-networks-explained.html
-
9 Key Deep Learning Papers, Explained">9 Key Deep Learning Papers, Explained
If you are interested in understanding the current state of deep learning, this post outlines and thoroughly summarizes 9 of the most influential contemporary papers in the field.https://www.kdnuggets.com/2016/09/9-key-deep-learning-papers-explained.html
-
A Beginner’s Guide to Neural Networks with R!
In this article we will learn how Neural Networks work and how to implement them with the R programming language! We will see how we can easily create Neural Networks with R and even visualize them. Basic understanding of R is necessary to understand this article.https://www.kdnuggets.com/2016/08/begineers-guide-neural-networks-r.html
-
5 Deep Learning Projects You Can No Longer Overlook
There are a number of "mainstream" deep learning projects out there, but many more niche projects flying under the radar. Have a look at 5 such projects worth checking out.https://www.kdnuggets.com/2016/07/five-deep-learning-projects-cant-overlook.html
-
What is the Difference Between Deep Learning and “Regular” Machine Learning?">What is the Difference Between Deep Learning and “Regular” Machine Learning?
Another concise explanation of a machine learning concept by Sebastian Raschka. This time, Sebastian explains the difference between Deep Learning and "regular" machine learning.https://www.kdnuggets.com/2016/06/difference-between-deep-learning-regular-machine-learning.html
-
The Amazing Power of Word Vectors
A fantastic overview of several now-classic papers on word2vec, the work of Mikolov et al. at Google on efficient vector representations of words, and what you can do with them.https://www.kdnuggets.com/2016/05/amazing-power-word-vectors.html
-
Deep Learning for Internet of Things Using H2O
H2O is feature-rich open source machine learning platform known for its R and Spark integration and it’s ease of use. This is an overview of using H2O deep learning for data science with the Internet of Things.https://www.kdnuggets.com/2016/04/deep-learning-iot-h2o.html
-
Must Know Tips for Deep Learning Neural Networks
Deep learning is white hot research topic. Add some solid deep learning neural network tips and tricks from a PhD researcher.https://www.kdnuggets.com/2016/03/must-know-tips-deep-learning-part-1.html
-
How do Neural Networks Learn?
Neural networks are generating a lot of excitement, while simultaneously posing challenges to people trying to understand how they work. Visualize how neural nets work from the experience of implementing a real world project.https://www.kdnuggets.com/2015/12/how-do-neural-networks-learn.html
-
Understanding Convolutional Neural Networks for NLP
Dive into the world of Convolution Neural Networks (CNN), learn how they work, how to apply them for NLP, and how to tune CNN hyperparameters for best performance.https://www.kdnuggets.com/2015/11/understanding-convolutional-neural-networks-nlp.html
-
Top 20 Python Machine Learning Open Source Projects
We examine top Python Machine learning open source projects on Github, both in terms of contributors and commits, and identify most popular and most active ones.https://www.kdnuggets.com/2015/06/top-20-python-machine-learning-open-source-projects.html
-
WTF is Regularization and What is it For?
This article explains the concept of regularization and its significance in machine learning and deep learning. We have discussed how regularization can be used to enhance the performance of linear models, as well as how it can be applied to improve the performance of deep learning models.https://www.kdnuggets.com/wtf-is-regularization-and-what-is-it-for
-
Building a Convolutional Neural Network with PyTorch
This blog post provides a tutorial on constructing a convolutional neural network for image classification in PyTorch, leveraging convolutional and pooling layers for feature extraction as well as fully-connected layers for prediction.https://www.kdnuggets.com/building-a-convolutional-neural-network-with-pytorch
-
From Zero to Hero: Create Your First ML Model with PyTorch
Learn the PyTorch basics by building a classification model from scratch.https://www.kdnuggets.com/from-zero-to-hero-create-your-first-ml-model-with-pytorch
-
A Comprehensive Guide to Convolutional Neural Networks
Artificial Intelligence has been witnessing monumental growth in bridging the gap between the capabilities of humans and machines. Researchers and enthusiasts alike, work on numerous aspects of the field to make amazing things happen. One of many such areas is the domain of Computer Vision.https://www.kdnuggets.com/2023/06/comprehensive-guide-convolutional-neural-networks.html
-
A Deep Dive into GPT Models: Evolution & Performance Comparison
The blog focuses on GPT models, providing an in-depth understanding and analysis. It explains the three main components of GPT models: generative, pre-trained, and transformers.https://www.kdnuggets.com/2023/05/deep-dive-gpt-models.html
-
Should The Data Warehouse Be Immutable?
Is the data warehouse broken? Is the "immutable data warehouse" the right path for your data team? Learn more here.https://www.kdnuggets.com/2022/05/data-warehouse-immutable.html
-
Machine Learning Key Terms, Explained
Read this overview of 12 important machine learning concepts, presented in a no frills, straightforward definition style.https://www.kdnuggets.com/2016/05/machine-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
-
On-Device Deep Learning: PyTorch Mobile and TensorFlow Lite
PyTorch and TensorFlow are the two leading AI/ML Frameworks. In this article, we take a look at their on-device counterparts PyTorch Mobile and TensorFlow Lite and examine them more deeply from the perspective of someone who wishes to develop and deploy models for use on mobile platforms.https://www.kdnuggets.com/2021/11/on-device-deep-learning-pytorch-mobile-tensorflow-lite.html
-
Advanced PyTorch Lightning with TorchMetrics and Lightning Flash
In this tutorial we will be diving deeper into two additional tools you should be using: TorchMetrics and Lightning Flash. TorchMetrics unsurprisingly provides a modular approach to define and track useful metrics across batches and devices, while Lightning Flash offers a suite of functionality facilitating more efficient transfer learning and data handling, and a recipe book of state-of-the-art approaches to typical deep learning problems.https://www.kdnuggets.com/2021/11/advanced-pytorch-lightning-torchmetrics-lightning-flash.html
-
Learn To Reproduce Papers: Beginner’s Guide">Learn To Reproduce Papers: Beginner’s Guide
Step-by-step instructions on how to understand Deep Learning papers and implement the described approaches.https://www.kdnuggets.com/2021/10/learn-reproduce-papers-beginners-guide.html
-
New Computing Paradigm for AI: Processing-in-Memory (PIM) Architecture
As larger deep neural networks are trained on the latest and fastest chip technologies, an important challenge remains that bottlenecks performance -- and it is not compute power. You can try to calculate a DNN as fast as possible, but there is data -- and it has to move. Data pipelines on the chip are expensive and new solutions must be developed to advance capabilities.https://www.kdnuggets.com/2021/10/samsung-computing-paradigm-ai-in-memory.html
-
Introducing TensorFlow Similarity
TensorFlow Similarity is a newly-released library from Google that facilitates the training, indexing and querying of similarity models. Check out more here.https://www.kdnuggets.com/2021/09/introducing-tensorflow-similarity.html
-
Multilabel Document Categorization, step by step example
This detailed guide explores an unsupervised and supervised learning two-stage approach with LDA and BERT to develop a domain-specific document categorizer on unlabeled documents.https://www.kdnuggets.com/2021/08/multilabel-document-categorization.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
-
7 Open Source Libraries for Deep Learning Graphs
In this article we’ll go through 7 up-and-coming open source libraries for graph deep learning, ranked in order of increasing popularity.https://www.kdnuggets.com/2021/07/7-open-source-libraries-deep-learning-graphs.html
-
Exploring the SwAV Method
This post discusses the SwAV (Swapping Assignments between multiple Views of the same image) method from the paper “Unsupervised Learning of Visual Features by Contrasting Cluster Assignments” by M. Caron et al.https://www.kdnuggets.com/2021/07/swav-method.html
-
High-Performance Deep Learning: How to train smaller, faster, and better models – Part 4
With the right software, hardware, and techniques at your fingertips, your capability to effectively develop high-performing models now hinges on leveraging automation to expedite the experimental process and building with the most efficient model architectures for your data.https://www.kdnuggets.com/2021/07/high-performance-deep-learning-part4.html
-
High-Performance Deep Learning: How to train smaller, faster, and better models – Part 3
Now that you are ready to efficiently build advanced deep learning models with the right software and hardware tools, the techniques involved in implementing such efforts must be explored to improve model quality and obtain the performance that your organization desires.https://www.kdnuggets.com/2021/07/high-performance-deep-learning-part3.html
-
Computational Complexity of Deep Learning: Solution Approaches
Why has deep learning been so successful? What is the fundamental reason that deep learning can learn from big data? Why cannot traditional ML learn from the large data sets that are now available for different tasks as efficiently as deep learning can?https://www.kdnuggets.com/2021/06/computational-complexity-deep-learning-solution-approaches.html
-
Beginners Guide to Debugging TensorFlow Models
If you are new to working with a deep learning framework, such as TensorFlow, there are a variety of typical errors beginners face when building and training models. Here, we explore and solve some of the most common errors to help you develop a better intuition for debugging in TensorFlow.https://www.kdnuggets.com/2021/06/beginners-guide-debugging-tensorflow-models.html
-
How to Apply Transformers to Any Length of Text
Read on to find how to restore the power of NLP for long sequences.https://www.kdnuggets.com/2021/04/apply-transformers-any-length-text.html
-
How to deploy Machine Learning/Deep Learning models to the web">How to deploy Machine Learning/Deep Learning models to the web
The full value of your deep learning models comes from enabling others to use them. Learn how to deploy your model to the web and access it as a REST API, and begin to share the power of your machine learning development with the world.https://www.kdnuggets.com/2021/04/deploy-machine-learning-models-to-web.html
-
Deep learning doesn’t need to be a black box">Deep learning doesn’t need to be a black box
The cultural perception of AI is often suspect because of the described challenges in knowing why a deep neural network makes its predictions. So, researchers try to crack open this "black box" after a network is trained to correlate results with inputs. But, what if the goal of explainability could be designed into the network's architecture -- before the model is trained and without reducing its predictive power? Maybe the box could stay open from the beginning.https://www.kdnuggets.com/2021/02/deep-learning-not-black-box.html
-
Saving and loading models in TensorFlow — why it is important and how to do it
So much time and effort can go into training your machine learning models. But, shut down the notebook or system, and all those trained weights and more vanish with the memory flush. Saving your models to maximize reusability is key for efficient productivity.https://www.kdnuggets.com/2021/02/saving-loading-models-tensorflow.html
-
Working With The Lambda Layer in Keras
In this tutorial we'll cover how to use the Lambda layer in Keras to build, save, and load models which perform custom operations on your data.https://www.kdnuggets.com/2021/01/working-lambda-layer-keras.html
-
10 Underappreciated Python Packages for Machine Learning Practitioners">10 Underappreciated Python Packages for Machine Learning Practitioners
Here are 10 underappreciated Python packages covering neural architecture design, calibration, UI creation and dissemination.https://www.kdnuggets.com/2021/01/10-underappreciated-python-packages-machine-learning-practitioners.html
-
How to Create Custom Real-time Plots in Deep Learning
How to generate real-time visualizations of custom metrics while training a deep learning model using Keras callbacks.https://www.kdnuggets.com/2020/12/create-custom-real-time-plots-deep-learning.html
-
Learn Deep Learning with this Free Course from Yann LeCun">Learn Deep Learning with this Free Course from Yann LeCun
Here is a freely-available NYU course on deep learning to check out from Yann LeCun and Alfredo Canziani, including videos, slides, and other helpful resources.https://www.kdnuggets.com/2020/11/learn-deep-learning-free-course-yann-lecun.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
-
Showcasing the Benefits of Software Optimizations for AI Workloads on Intel® Xeon® Scalable Platforms
The focus of this blog is to bring to light that continued software optimizations can boost performance not only for the latest platforms, but also for the current install base from prior generations. This means customers can continue to extract value from their current platform investments.https://www.kdnuggets.com/2020/09/showcasing-benefits-software-optimizations-ai-workloads-intel.html
-
4 ways to improve your TensorFlow model – key regularization techniques you need to know">4 ways to improve your TensorFlow model – key regularization techniques you need to know
Regularization techniques are crucial for preventing your models from overfitting and enables them perform better on your validation and test sets. This guide provides a thorough overview with code of four key approaches you can use for regularization in TensorFlow.https://www.kdnuggets.com/2020/08/tensorflow-model-regularization-techniques.html
-
Crop Disease Detection Using Machine Learning and Computer Vision
Computer vision has tremendous promise for improving crop monitoring at scale. We present our learnings from building such models for detecting stem and wheat rust in crops.https://www.kdnuggets.com/2020/06/crop-disease-detection-computer-vision.html
-
How Deep Learning is Accelerating Drug Discovery in Pharmaceuticals">How Deep Learning is Accelerating Drug Discovery in Pharmaceuticals
The goal of this essay is to discuss meaningful machine learning progress in the real-world application of drug discovery. There’s even a solid chance of the deep learning approach to drug discovery changing lives for the better doing meaningful good in the world.https://www.kdnuggets.com/2020/04/deep-learning-accelerating-drug-discovery-pharmaceuticals.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
-
Why BERT Fails in Commercial Environments
The deployment of large transformer-based models in dynamic commercial environments often yields poor results. This is because commercial environments are usually dynamic, and contain continuous domain shifts between inference and training data.https://www.kdnuggets.com/2020/03/bert-fails-commercial-environments.html
-
The 4 Best Jupyter Notebook Environments for Deep Learning
Many cloud providers, and other third-party services, see the value of a Jupyter notebook environment which is why many companies now offer cloud hosted notebooks that are hosted on the cloud. Let's have a look at 3 such environments.https://www.kdnuggets.com/2020/03/4-best-jupyter-notebook-environments-deep-learning.html
-
Decision Boundary for a Series of Machine Learning Models
I train a series of Machine Learning models using the iris dataset, construct synthetic data from the extreme points within the data and test a number of Machine Learning models in order to draw the decision boundaries from which the models make predictions in a 2D space, which is useful for illustrative purposes and understanding on how different Machine Learning models make predictions.https://www.kdnuggets.com/2020/03/decision-boundary-series-machine-learning-models.html
-
Recreating Fingerprints using Convolutional Autoencoders
The article gets you started working with fingerprints using Deep Learning.https://www.kdnuggets.com/2020/03/recreating-fingerprints-using-convolutional-autoencoders.html
-
Audio Data Analysis Using Deep Learning with Python (Part 2)
This is a followup to the first article in this series. Once you are comfortable with the concepts explained in that article, you can come back and continue with this.https://www.kdnuggets.com/2020/02/audio-data-analysis-deep-learning-python-part-2.html
-
Audio Data Analysis Using Deep Learning with Python (Part 1)">Audio Data Analysis Using Deep Learning with Python (Part 1)
A brief introduction to audio data processing and genre classification using Neural Networks and python.https://www.kdnuggets.com/2020/02/audio-data-analysis-deep-learning-python-part-1.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
-
Create Your Own Computer Vision Sandbox
This post covers a wide array of computer vision tasks, from automated data collection to CNN model building.https://www.kdnuggets.com/2020/02/computer-vision-sandbox.html
-
Exoplanet Hunting Using Machine Learning
Search for exoplanets — those planets beyond our own solar system — using machine learning, and implement these searches in Python.https://www.kdnuggets.com/2020/01/exoplanet-hunting-machine-learning.html
-
NLP Year in Review — 2019
In this blog post, I want to highlight some of the most important stories related to machine learning and NLP that I came across in 2019.https://www.kdnuggets.com/2020/01/nlp-year-review-2019.html
-
Explaining Black Box Models: Ensemble and Deep Learning Using LIME and SHAP
This article will demonstrate explainability on the decisions made by LightGBM and Keras models in classifying a transaction for fraudulence, using two state of the art open source explainability techniques, LIME and SHAP.https://www.kdnuggets.com/2020/01/explaining-black-box-models-ensemble-deep-learning-lime-shap.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
-
Google’s New Explainable AI Service">Google’s New Explainable AI Service
Google has started offering a new service for “explainable AI” or XAI, as it is fashionably called. Presently offered tools are modest, but the intent is in the right direction.https://www.kdnuggets.com/2019/12/googles-new-explainable-ai-service.html
-
Google Open Sources MobileNetV3 with New Ideas to Improve Mobile Computer Vision Models
The latest release of MobileNets incorporates AutoML and other novel ideas in mobile deep learning.https://www.kdnuggets.com/2019/12/google-open-sources-mobilenetv3-improve-mobile-computer-vision-models.html
-
Automated Machine Learning Project Implementation Complexities">Automated Machine Learning Project Implementation Complexities
To demonstrate the implementation complexity differences along the AutoML highway, let's have a look at how 3 specific software projects approach the implementation of just such an AutoML "solution," namely Keras Tuner, AutoKeras, and automl-gs.https://www.kdnuggets.com/2019/11/automl-implementation-complexities.html
-
Transfer Learning Made Easy: Coding a Powerful Technique
While the revolution of deep learning now impacts our daily lives, these networks are expensive. Approaches in transfer learning promise to ease this burden by enabling the re-use of trained models -- and this hands-on tutorial will walk you through a transfer learning technique you can run on your laptop.https://www.kdnuggets.com/2019/11/transfer-learning-coding.html
-
Facebook Has Been Quietly Open Sourcing Some Amazing Deep Learning Capabilities for PyTorch">Facebook Has Been Quietly Open Sourcing Some Amazing Deep Learning Capabilities for PyTorch
The new release of PyTorch includes some impressive open source projects for deep learning researchers and developers.https://www.kdnuggets.com/2019/11/facebook-quietly-open-sourcing-amazing-deep-learning-capabilities-pytorch.html
-
Research Guide for Video Frame Interpolation with Deep Learning
In this research guide, we’ll look at deep learning papers aimed at synthesizing video frames within an existing video.https://www.kdnuggets.com/2019/10/research-guide-video-frame-interpolation-deep-learning.html
-
Using Neural Networks to Design Neural Networks: The Definitive Guide to Understand Neural Architecture Search
A recent survey outlined the main neural architecture search methods used to automate the design of deep learning systems.https://www.kdnuggets.com/2019/10/using-neural-networks-design-neural-networks-definitive-guide-understand-neural-architecture-search.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
-
Applying Data Science to Cybersecurity Network Attacks & Events
Check out this detailed tutorial on applying data science to the cybersecurity domain, written by an individual with backgrounds in both fields.https://www.kdnuggets.com/2019/09/applying-data-science-cybersecurity-network-attacks-events.html
-
Can graph machine learning identify hate speech in online social networks?
Online hate speech is a complex subject. Follow this demonstration using state-of-the-art graph neural network models to detect hateful users based on their activities on the Twitter social network.https://www.kdnuggets.com/2019/09/graph-machine-learning-hate-speech-social-networks.html
-
Order Matters: Alibaba’s Transformer-based Recommender System
Alibaba, the largest e-commerce platform in China, is a powerhouse not only when it comes to e-commerce, but also when it comes to recommender systems research. Their latest paper, Behaviour Sequence Transformer for E-commerce Recommendation in Alibaba, is yet another publication that pushes the state of the art in recommender systems.https://www.kdnuggets.com/2019/08/order-matters-alibabas-transformer-based-recommender-system.html
-
Understanding Cancer using Machine Learning">Understanding Cancer using Machine Learning
Use of Machine Learning (ML) in Medicine is becoming more and more important. One application example can be Cancer Detection and Analysis.https://www.kdnuggets.com/2019/08/understanding-cancer-machine-learning.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
-
This New Google Technique Help Us Understand How Neural Networks are Thinking">This New Google Technique Help Us Understand How Neural Networks are Thinking
Recently, researchers from the Google Brain team published a paper proposing a new method called Concept Activation Vectors (CAVs) that takes a new angle to the interpretability of deep learning models.https://www.kdnuggets.com/2019/07/google-technique-understand-neural-networks-thinking.html
-
Adapters: A Compact and Extensible Transfer Learning Method for NLP
Adapters obtain comparable results to BERT on several NLP tasks while achieving parameter efficiency.https://www.kdnuggets.com/2019/07/adapters-compact-extensible-transfer-learning-method-nlp.html
-
Practical Speech Recognition with Python: The Basics
Do you fear implementing speech recognition in your Python apps? Read this tutorial for a simple approach to getting practical with speech recognition using open source Python libraries.https://www.kdnuggets.com/2019/07/practical-speech-recognition-python-basics.html
-
10 New Things I Learnt from fast.ai Course V3
Fastai offers some really good courses in machine learning and deep learning for programmers. I recently took their "Practical Deep Learning for Coders" course and found it really interesting. Here are my learnings from the course.https://www.kdnuggets.com/2019/06/things-learnt-fastai-course.html
-
The Emergence of Cooperative and Competitive AI Agents
Without specific training in collaboration or competition, a recent AI model from DeepMind uses reinforcement learning to evolve these behaviors in game-playing agents. Learn how this emergent collective intelligence outperforms their human counterparts in 3D multiplayer games.https://www.kdnuggets.com/2019/06/emergence-cooperative-competitive-ai-agents.html
-
Customer Churn Prediction Using Machine Learning: Main Approaches and Models
We reach out to experts from HubSpot and ScienceSoft to discuss how SaaS companies handle the problem of customer churn prediction using Machine Learning.https://www.kdnuggets.com/2019/05/churn-prediction-machine-learning.html
-
An introduction to explainable AI, and why we need it
We introduce explainable AI, why it is needed, and present the Reversed Time Attention Model, Local Interpretable Model-Agnostic Explanation and Layer-wise Relevance Propagation.https://www.kdnuggets.com/2019/04/introduction-explainable-ai.html
-
Checklist for Debugging Neural Networks
Check out these tangible steps you can take to identify and fix issues with training, generalization, and optimization for machine learning models.https://www.kdnuggets.com/2019/03/checklist-debugging-neural-networks.html
-
How to Train a Keras Model 20x Faster with a TPU for Free
This post shows how to train an LSTM Model using Keras and Google CoLaboratory with TPUs to exponentially reduce training time compared to a GPU on your local machine.https://www.kdnuggets.com/2019/03/train-keras-model-20x-faster-tpu-free.html
-
Beating the Bookies with Machine Learning
We investigate how to use a custom loss function to identify fair odds, including a detailed example using machine learning to bet on the results of a darts match and how this can assist you in beating the bookmaker.https://www.kdnuggets.com/2019/03/beating-bookies-machine-learning.html
-
State of the art in AI and Machine Learning – highlights of papers with code
We introduce papers with code, the free and open resource of state-of-the-art Machine Learning papers, code and evaluation tables.https://www.kdnuggets.com/2019/02/paperswithcode-ai-machine-learning-highlights.html
-
Explainable Artificial Intelligence
We outline the necessity of explainable AI, discuss some of the methods in academia, take a look at explainability vs accuracy, investigate use cases, and more.https://www.kdnuggets.com/2019/01/explainable-ai.html
-
Solve any Image Classification Problem Quickly and Easily
This article teaches you how to use transfer learning to solve image classification problems. A practical example using Keras and its pre-trained models is given for demonstration purposes.https://www.kdnuggets.com/2018/12/solve-image-classification-problem-quickly-easily.html
-
Using Uncertainty to Interpret your Model
We outline why you should care about uncertainty and discuss the different types, including model, data and measurement uncertainty and what different purposes these all serve.https://www.kdnuggets.com/2018/11/using-uncertainty-interpret-model.html
-
Building an Image Classifier Running on Raspberry Pi
The tutorial starts by building the Physical network connecting Raspberry Pi to the PC via a router. After preparing their IPv4 addresses, SSH session is created for remotely accessing of the Raspberry Pi. After uploading the classification project using FTP, clients can access it using web browsers for classifying images.https://www.kdnuggets.com/2018/10/building-image-classifier-running-raspberry-pi.html
-
Basic Image Data Analysis Using Python – Part 3
Accessing the internal component of digital images using Python packages becomes more convenient to help understand its properties, as well as nature.https://www.kdnuggets.com/2018/09/image-data-analysis-python-p3.html
-
Power Laws in Deep Learning
In pretrained, production quality DNNs, the weight matrices for the Fully Connected (FC ) layers display Fat Tailed Power Law behavior.https://www.kdnuggets.com/2018/09/power-laws-deep-learning.html
-
Interpreting a data set, beginning to end
Detailed knowledge of your data is key to understanding it! We review several important methods that to understand the data, including summary statistics with visualization, embedding methods like PCA and t-SNE, and Topological Data Analysis.https://www.kdnuggets.com/2018/08/interpreting-data-set.html
-
Only Numpy: Implementing GANs and Adam Optimizer using Numpy">Only Numpy: Implementing GANs and Adam Optimizer using Numpy
This post is an implementation of GANs and the Adam optimizer using only Python and Numpy, with minimal focus on the underlying maths involved.https://www.kdnuggets.com/2018/08/only-numpy-implementing-gans-adam-optimizer.html
-
fast.ai Deep Learning Part 2 Complete Course Notes
This posts is a collection of a set of fantastic notes on the fast.ai deep learning part 2 MOOC freely available online, as written and shared by a student. These notes are a valuable learning resource either as a supplement to the courseware or on their own.https://www.kdnuggets.com/2018/07/fast-ai-deep-learning-part-2-notes.html
-
Overview and benchmark of traditional and deep learning models in text classification
In this post, traditional and deep learning models in text classification will be thoroughly investigated, including a discussion into both Recurrent and Convolutional neural networks.https://www.kdnuggets.com/2018/07/overview-benchmark-deep-learning-models-text-classification.html
-
Inside the Mind of a Neural Network with Interactive Code in Tensorflow
Understand the inner workings of neural network models as this post covers three related topics: histogram of weights, visualizing the activation of neurons, and interior / integral gradients.https://www.kdnuggets.com/2018/06/inside-mind-neural-network-interactive-code-tensorflow.html
-
Building a Basic Keras Neural Network Sequential Model
The approach basically coincides with Chollet's Keras 4 step workflow, which he outlines in his book "Deep Learning with Python," using the MNIST dataset, and the model built is a Sequential network of Dense layers. A building block for additional posts.https://www.kdnuggets.com/2018/06/basic-keras-neural-network-sequential-model.html
-
Using Topological Data Analysis to Understand the Behavior of Convolutional Neural Networks
Neural Networks are powerful but complex and opaque tools. Using Topological Data Analysis, we can describe the functioning and learning of a convolutional neural network in a compact and understandable way.https://www.kdnuggets.com/2018/06/topological-data-analysis-convolutional-neural-networks.html
-
Batch Normalization in Neural Networks
This article explains batch normalization in a simple way. I wrote this article after what I learned from Fast.ai and deeplearning.ai.https://www.kdnuggets.com/2018/06/batch-normalization-neural-networks.html
-
Taming LSTMs: Variable-sized mini-batches and why PyTorch is good for your health
After reading this, you’ll be back to fantasies of you + PyTorch eloping into the sunset while your Recurrent Networks achieve new accuracies you’ve only read about on Arxiv.https://www.kdnuggets.com/2018/06/taming-lstms-variable-sized-mini-batches-pytorch.html