Search results for deep learning

Found 2824 documents, 5968 searched:

• A Layman’s Guide to Data Science. Part 2: How to Build a Data Project

  As Part 2 in a Guide to Data Science, we outline the steps to build your first Data Science project, including how to ask good questions to understand the data first, how to prepare the data, how to develop an MVP, reiterate to build a good product, and, finally, present your project.

  https://www.kdnuggets.com/2020/04/guide-data-science-build-data-project.html

• Advice for a Successful Data Science Career

  This blog is meant to show that most everyone has had to expend quite a bit of effort to get where they are. They have to work hard, sometimes experience failure, show discipline, be persistent, be dedicated to their goals, and sometimes sacrifice or take risks.

  https://www.kdnuggets.com/2020/03/advice-successful-data-science-career.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

• Skynet Is Real: The History and Future of Factories With No Workers

  Let’s see whether robots will become "grave diggers" of the proletariat, what do we lack to get total automation, and what compromises exist.

  https://www.kdnuggets.com/2020/03/skynet-real-history-future-factories-no-workers.html

• Tokenization and Text Data Preparation with TensorFlow & Keras

  This article will look at tokenizing and further preparing text data for feeding into a neural network using TensorFlow and Keras preprocessing tools.

  https://www.kdnuggets.com/2020/03/tensorflow-keras-tokenization-text-data-prep.html

• TensorFlow 2.0 Tutorial: Optimizing Training Time Performance

  Tricks to improve TensorFlow training time with tf.data pipeline optimizations, mixed precision training and multi-GPU strategies.

  https://www.kdnuggets.com/2020/03/tensorflow-optimizing-training-time-performance.html

• Decision Tree Intuition: From Concept to Application

  While the use of Decision Trees in machine learning has been around for awhile, the technique remains powerful and popular. This guide first provides an introductory understanding of the method and then shows you how to construct a decision tree, calculate important analysis parameters, and plot the resulting tree.

  https://www.kdnuggets.com/2020/02/decision-tree-intuition.html

• Introducing fastpages: An easy to use blogging platform with extra features for Jupyter Notebooks

  This article introduces the easy to use blogging platform fastpages. fastpages relies on Github pages for hosting, and Github Actions to automate the creation of your blog, and contains extra features for Jupyter Notebooks.

  https://www.kdnuggets.com/2020/02/introducing-fastpages-blogging-platform-jupyter-notebooks.html

• Image Recognition and Object Detection in Retail

  “According to Gartner, by 2020, 85% of customer interactions in the retail industry will be managed by AI.”

  https://www.kdnuggets.com/2020/02/image-recognition-object-detection-retail.html

• Using the Fitbit Web API with Python

  Fitbit provides a Web API for accessing data from Fitbit activity trackers. Check out this updated tutorial to accessing this Fitbit data using the API with Python.

  https://www.kdnuggets.com/2020/02/using-fitbit-web-api-python.html

• Using AI to Identify Wildlife in Camera Trap Images from the Serengeti

  With recent developments in machine learning and computer vision, we acquired the tools to provide the biodiversity community with an ability to tap the potential of the knowledge generated automatically with systems triggered by a combination of heat and motion.

  https://www.kdnuggets.com/2020/02/using-ai-identify-wildlife-images-serengeti.html

• Easy Image Dataset Augmentation with TensorFlow

  What can we do when we don't have a substantial amount of varied training data? This is a quick intro to using data augmentation in TensorFlow to perform in-memory image transformations during model training to help overcome this data impediment.

  https://www.kdnuggets.com/2020/02/easy-image-dataset-augmentation-tensorflow.html

• Why Did I Reject a Data Scientist Job?">Why Did I Reject a Data Scientist Job?

  Snagging that job as a Data Scientist might not be exactly what you were expecting. Consider this advice on carefully considering job titles with what the position might really be like day-to-day.

  https://www.kdnuggets.com/2020/02/why-reject-data-scientist-job.html

• Observability for Data Engineering

  Going beyond traditional monitoring techniques and goals, understanding if a system is working as intended requires a new concept in DevOps, called Observability. Learn more about this essential approach to bring more context to your system metrics.

  https://www.kdnuggets.com/2020/02/observability-data-engineering.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

• Data Scientist Archetypes

  My goal here is to give you a map for navigating the sprawling terrain of data science. It’s to help you prioritize what you want to learn and what you want to do, so you don’t feel lost.

  https://www.kdnuggets.com/2020/01/data-scientist-archetypes.html

• Top Stories, Jan 13-19: Math for Programmers!; Decision Tree Algorithm, Explained

  Also: Top 9 Mobile Apps for Learning and Practicing Data Science; Classify A Rare Event Using 5 Machine Learning Algorithms; The Future of Machine Learning; The Book to Start You on Machine Learning

  https://www.kdnuggets.com/2020/01/top-news-week-0113-0119.html

• We Created a Lazy AI

  This article is an overview of how to design and implement reinforcement learning for the real world.

  https://www.kdnuggets.com/2020/01/created-lazy-ai.html

• Handling Trees in Data Science Algorithmic Interview

  This post is about fast-tracking the study and explanation of tree concepts for the data scientists so that you breeze through the next time you get asked these in an interview.

  https://www.kdnuggets.com/2020/01/handling-trees-data-science-algorithmic-interview.html

• How to Convert a Picture to Numbers

  Reducing images to numbers makes them amenable to computation. Let's take a look at the why and the how using Python and Numpy.

  https://www.kdnuggets.com/2020/01/convert-picture-numbers.html

• How To “Ultralearn” Data Science: summary, for those in a hurry">How To “Ultralearn” Data Science: summary, for those in a hurry

  For those of you in a hurry and interested in ultralearning (which should be all of you), this recap reviews the approach and summarizes its key elements -- focus, optimization, and deep understanding with experimentation -- geared toward learning Data Science.

  https://www.kdnuggets.com/2019/12/ultralearn-data-science-summary.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

• How To “Ultralearn” Data Science: removing distractions and finding focus, Part 2

  This second part in a series about how to "ultralearn" data science will guide you through several techniques to remove those distractions -- because your focus needs more focus.

  https://www.kdnuggets.com/2019/12/ultralearn-data-science-distractions-focus-part2.html

• How To “Ultralearn” Data Science, Part 1

  What is "ultralearning" and how can you follow the strategy to become an expert of data science? Start with this first part in a series that will guide you through this self-motivated methodology to help you efficiently master difficult skills.

  https://www.kdnuggets.com/2019/12/ultralearn-data-science-part1.html

• Explainability: Cracking open the black box, Part 1

  What is Explainability in AI and how can we leverage different techniques to open the black box of AI and peek inside? This practical guide offers a review and critique of the various techniques of interpretability.

  https://www.kdnuggets.com/2019/12/explainability-black-box-part1.html

• Markov Chains: How to Train Text Generation to Write Like George R. R. Martin

  Read this article on training Markov chains to generate George R. R. Martin style text.

  https://www.kdnuggets.com/2019/11/markov-chains-train-text-generation.html

• The Notebook Anti-Pattern

  This article aims to explain why this drive towards the use of notebooks in production is an anti pattern, giving some suggestions along the way.

  https://www.kdnuggets.com/2019/11/notebook-anti-pattern.html

• The Math Behind Bayes

  This post will be dedicated to explaining the maths behind Bayes Theorem, when its application makes sense, and its differences with Maximum Likelihood.

  https://www.kdnuggets.com/2019/11/math-behind-bayes.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

• Time Series Analysis: A Simple Example with KNIME and Spark

  The task: train and evaluate a simple time series model using a random forest of regression trees and the NYC Yellow taxi dataset.

  https://www.kdnuggets.com/2019/10/time-series-analysis-simple-example-knime-spark.html

• An Overview of Density Estimation

  Density estimation is estimating the probability density function of the population from the sample. This post examines and compares a number of approaches to density estimation.

  https://www.kdnuggets.com/2019/10/overview-density-estimation.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

• Sentiment and Emotion Analysis for Beginners: Types and Challenges

  There are three types of emotion AI, and their combinations. In this article, I’ll briefly go through these three types and the challenges of their real-life applications.

  https://www.kdnuggets.com/2019/10/sentiment-emotion-analysis-beginners-types-challenges.html

• The Future of Analytics and Data Science">The Future of Analytics and Data Science

  Learn about the current and future issues of data science and possible solutions from this interview with IADSS Co-founder, Dr. Usama Fayyad following his keynote speech at ODSC Boston 2019.

  https://www.kdnuggets.com/2019/09/future-analytics-data-science.html

• A Friendly Introduction to Support Vector Machines

  This article explains the Support Vector Machines (SVM) algorithm in an easy way.

  https://www.kdnuggets.com/2019/09/friendly-introduction-support-vector-machines.html

• What’s the difference between analytics and statistics?

  From asking the best questions about data to answering those questions with certainty, understanding the value of these two seemingly different professions is clarified when you see how they should work together.

  https://www.kdnuggets.com/2019/09/difference-analytics-statistics.html

• I wasn’t getting hired as a Data Scientist. So I sought data on who is.">I wasn’t getting hired as a Data Scientist. So I sought data on who is.

  Instead of focusing on skills thought to be required of data scientists, we can look at what they have actually done before.

  https://www.kdnuggets.com/2019/09/getting-hired-data-scientist-sought-data.html

• 4 Tips for Advanced Feature Engineering and Preprocessing

  Techniques for creating new features, detecting outliers, handling imbalanced data, and impute missing values.

  https://www.kdnuggets.com/2019/08/4-tips-advanced-feature-engineering-preprocessing.html

• A 2019 Guide to Human Pose Estimation

  Human pose estimation refers to the process of inferring poses in an image. Essentially, it entails predicting the positions of a person’s joints in an image or video. This problem is also sometimes referred to as the localization of human joints.

  https://www.kdnuggets.com/2019/08/2019-guide-human-pose-estimation.html

• Gender Diversity in AI Research

  Through an analysis of 1.5M papers from arXiv, this study reviews the evolution of gender diversity across disciplines, countries, and institutions as well as the semantic differences between AI papers with and without female co-authors.

  https://www.kdnuggets.com/2019/08/gender-diversity-ai-research.html

• Understanding Decision Trees for Classification in Python

  This tutorial covers decision trees for classification also known as classification trees, including the anatomy of classification trees, how classification trees make predictions, using scikit-learn to make classification trees, and hyperparameter tuning.

  https://www.kdnuggets.com/2019/08/understanding-decision-trees-classification-python.html

• Inside Pluribus: Facebook’s New AI That Just Mastered the World’s Most Difficult Poker Game

  The reasons why Pluribus represents a major breakthrough in AI systems might result confusing to many readers. After all, in recent years AI researchers have made tremendous progress across different complex games. However, six-player, no-limit Texas Hold’em still remains one of the most elusive challenges for AI systems.

  https://www.kdnuggets.com/2019/08/inside-pluribus-facebooks-new-ai-poker.html

• What is Benford’s Law and why is it important for data science?">What is Benford’s Law and why is it important for data science?

  Benford’s law is a little-known gem for data analytics. Learn about how this can be used for anomaly or fraud detection in scientific or technical publications.

  https://www.kdnuggets.com/2019/08/benfords-law-data-science.html

• Can we trust AutoML to go on full autopilot?

  We put an AutoML tool to the test on a real-world problem, and the results are surprising. Even with automatic machine learning, you still need expert data scientists.

  https://www.kdnuggets.com/2019/07/automl-full-autopilot.html

• 7 Tips for Dealing With Small Data

  At my workplace, we produce a lot of functional prototypes for our clients. Because of this, I often need to make Small Data go a long way. In this article, I’ll share 7 tips to improve your results when prototyping with small datasets.

  https://www.kdnuggets.com/2019/07/7-tips-dealing-small-data.html

• A Gentle Introduction to Noise Contrastive Estimation

  Find out how to use randomness to learn your data by using Noise Contrastive Estimation with this guide that works through the particulars of its implementation.

  https://www.kdnuggets.com/2019/07/introduction-noise-contrastive-estimation.html

• Is SQL needed to be a data scientist?

  As long as there is ‘data’ in data scientist, Structured Query Language (or see-quel as we call it) will remain an important part of it. In this blog, let us explore data science and its relationship with SQL.

  https://www.kdnuggets.com/2019/07/sql-needed-data-scientist.html

• Pre-training, Transformers, and Bi-directionality

  Bidirectional Encoder Representations from Transformers BERT (Devlin et al., 2018) is a language representation model that combines the power of pre-training with the bi-directionality of the Transformer’s encoder (Vaswani et al., 2017). BERT improves the state-of-the-art performance on a wide array of downstream NLP tasks with minimal additional task-specific training.

  https://www.kdnuggets.com/2019/07/pre-training-transformers-bi-directionality.html

• XGBoost and Random Forest® with Bayesian Optimisation

  This article will explain how to use XGBoost and Random Forest with Bayesian Optimisation, and will discuss the main pros and cons of these methods.

  https://www.kdnuggets.com/2019/07/xgboost-random-forest-bayesian-optimisation.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

• 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

• K-means Clustering with Dask: Image Filters for Cat Pictures

  How to recreate an original cat image with least possible colors. An interesting use case of Unsupervised Machine Learning with K Means Clustering in Python.

  https://www.kdnuggets.com/2019/06/k-means-clustering-dask-image-filters.html

• A Step-by-Step Guide to Transitioning your Career to Data Science – Part 2

  How do you identify the technical skills a hiring manager is looking for? How do you build a data science project that draws the attention of a hiring manager?

  https://www.kdnuggets.com/2019/06/guide-transitioning-career-data-science-part-2.html

• NLP and Computer Vision Integrated">NLP and Computer Vision Integrated

  Computer vision and NLP developed as separate fields, and researchers are now combining these tasks to solve long-standing problems across multiple disciplines.

  https://www.kdnuggets.com/2019/06/nlp-computer-vision-integrated.html

• Why physical storage of your database tables might matter

  Follow this investigation into why physical storage of your database tables might matter, from problem identification to possible issue resolutions.

  https://www.kdnuggets.com/2019/05/physical-storage-database-tables-might-matter.html

• Your Guide to Natural Language Processing (NLP)

  This extensive post covers NLP use cases, basic examples, Tokenization, Stop Words Removal, Stemming, Lemmatization, Topic Modeling, the future of NLP, and more.

  https://www.kdnuggets.com/2019/05/guide-natural-language-processing-nlp.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

• Graduating in GANs: Going From Understanding Generative Adversarial Networks to Running Your Own

  Read how generative adversarial networks (GANs) research and evaluation has developed then implement your own GAN to generate handwritten digits.

  https://www.kdnuggets.com/2019/04/graduating-gans-understanding-generative-adversarial-networks.html

• 2019 Best Masters in Data Science and Analytics – Online

  We provide an updated comprehensive and objective survey of online Masters in Analytics and Data Science, including rankings, tuition, and duration of the education program.

  https://www.kdnuggets.com/2019/04/best-masters-data-science-analytics-online.html

• Was it Worth Studying a Data Science Masters?

  As I started to apply for Data Science roles it quickly became apparent that I was lacking two key skills: applying Machine Learning and coding

  https://www.kdnuggets.com/2019/04/worth-studying-data-science-masters.html

• Data Visualization in Python: Matplotlib vs Seaborn">Data Visualization in Python: Matplotlib vs Seaborn

  Seaborn and Matplotlib are two of Python's most powerful visualization libraries. Seaborn uses fewer syntax and has stunning default themes and Matplotlib is more easily customizable through accessing the classes.

  https://www.kdnuggets.com/2019/04/data-visualization-python-matplotlib-seaborn.html

• How Optimization Works

  Optimization problems are naturally described in terms of costs - money, time, resources - rather than benefits. In math it's convenient to make all your problems look the same before you work out a solution, so that you can just solve it the one time.

  https://www.kdnuggets.com/2019/04/how-optimization-works.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

• How to DIY Your Data Science Education

  Some people find the path of formal education works well for them, but this may not work for everyone, in every situation. Here are eight ways that you can take a DIY approach to your data science education.

  https://www.kdnuggets.com/2019/04/diy-your-data-science-education.html

• 7 Qualities Your Big Data Visualization Tools Absolutely Must Have and 10 Tools That Have Them">7 Qualities Your Big Data Visualization Tools Absolutely Must Have and 10 Tools That Have Them

  Without the right visualization tools, raw data is of little use. Data visualization helps present the data in an interactive visual format. Here are the qualities to look for in a data visualization tool.

  https://www.kdnuggets.com/2019/04/7-qualities-big-data-visualization-tools.html

• How to Capture Data to Make Business Impact

  We take a look at the formula for calculating the efficiency of a data capturing method, before going onto explain the concept of Smart Data.

  https://www.kdnuggets.com/2019/03/capture-data-make-business-impact.html

• Top 8 Data Science Use Cases in Manufacturing

  Data science is said to change the manufacturing industry dramatically. Let's take under consideration several data science use cases in manufacturing that have already become common and brought benefits to the manufacturers.

  https://www.kdnuggets.com/2019/03/top-8-data-science-use-cases-manufacturing.html

• AI: Arms Race 2.0

  An analysis of the current state of the competition between US, Europe, and China in AI, examining research, patent publications, global datasphere, devices and IoT, people, and more.

  https://www.kdnuggets.com/2019/03/ai-arms-race-20.html

• The Pareto Principle for Data Scientists">The Pareto Principle for Data Scientists

  In this article, I’ll share a few ways in which we, as data scientists, can use the power of the Pareto Principle to guide our day-to-day activities.

  https://www.kdnuggets.com/2019/03/pareto-principle-data-scientists.html

• 3 Reasons Why AutoML Won’t Replace Data Scientists Yet

  We dispel the myth that AutoML is replacing Data Scientists jobs by highlighting three factors in Data Science development that AutoML can’t solve.

  https://www.kdnuggets.com/2019/03/why-automl-wont-replace-data-scientists.html

• Deconstructing BERT, Part 2: Visualizing the Inner Workings of Attention

  In this post, the author shows how BERT can mimic a Bag-of-Words model. The visualization tool from Part 1 is extended to probe deeper into the mind of BERT, to expose the neurons that give BERT its shape-shifting superpowers.

  https://www.kdnuggets.com/2019/03/deconstructing-bert-part-2-visualizing-inner-workings-attention.html

• GANs Need Some Attention, Too

  Self-Attention Generative Adversarial Networks (SAGAN; Zhang et al., 2018) are convolutional neural networks that use the self-attention paradigm to capture long-range spatial relationships in existing images to better synthesize new images.

  https://www.kdnuggets.com/2019/03/gans-need-some-attention-too.html

• On Building Effective Data Science Teams

  We take a look at the qualities that make a successful data team in order to help business leaders and executives create better AI strategies.

  https://www.kdnuggets.com/2019/03/building-effective-data-science-teams.html

• OpenAI’s GPT-2: the model, the hype, and the controversy

  OpenAI recently released a very large language model called GPT-2. Controversially, they decided not to release the data or the parameters of their biggest model, citing concerns about potential abuse. Read this researcher's take on the issue.

  https://www.kdnuggets.com/2019/03/openai-gpt-2-model-hype-controversy.html

• Top 7 Data Science Use Cases in Travel

  To satisfy all the needs of the growing number of consumers and process enormous data chunks, data science algorithms are vital. Let’s consider several of widespread and efficient data science use cases in the travel industry.

  https://www.kdnuggets.com/2019/02/top-7-data-science-use-cases-travel.html

• Deconstructing BERT: Distilling 6 Patterns from 100 Million Parameters

  Google’s BERT algorithm has emerged as a sort of “one model to rule them all.” BERT builds on two key ideas that have been responsible for many of the recent advances in NLP: (1) the transformer architecture and (2) unsupervised pre-training.

  https://www.kdnuggets.com/2019/02/deconstructing-bert-distilling-patterns-100-million-parameters.html

• Simple Yet Practical Data Cleaning Codes

  Real world data is messy and needs to be cleaned before it can be used for analysis. Industry experts say the data preprocessing step can easily take 70% to 80% of a data scientist's time on a project.

  https://www.kdnuggets.com/2019/02/simple-yet-practical-data-cleaning-codes.html

• Are BERT Features InterBERTible?

  This is a short analysis of the interpretability of BERT contextual word representations. Does BERT learn a semantic vector representation like Word2Vec?

  https://www.kdnuggets.com/2019/02/bert-features-interbertible.html

• The Analytics Engineer – new role in the data team

  In a constantly changing landscape and with many companies, the roles and responsibilities of data engineers, analysts, and data scientists are changing, forcing the introduction of a new role: The Analytics Engineer.

  https://www.kdnuggets.com/2019/02/analytics-engineer-data-team.html

• Data Science For Our Mental Development

  In this blog, I aim to generalize how AI can help us with mental development in the future as well as discuss some of the present-day solutions.

  https://www.kdnuggets.com/2019/02/data-science-mental-development.html

• Top 10 Technology Trends of 2019">Top 10 Technology Trends of 2019

  This article outlines 10 top trending technologies for 2019, a list which covers diverse topics such as security, IoT, reinforcement learning, energy sustainability, smart cities, and much more.

  https://www.kdnuggets.com/2019/02/top-10-technology-trends-2019.html

• Understanding Gradient Boosting Machines">Understanding Gradient Boosting Machines

  However despite its massive popularity, many professionals still use this algorithm as a black box. As such, the purpose of this article is to lay an intuitive framework for this powerful machine learning technique.

  https://www.kdnuggets.com/2019/02/understanding-gradient-boosting-machines.html

• The Essential Data Science Venn Diagram">The Essential Data Science Venn Diagram

  A deeper examination of the interdisciplinary interplay involved in data science, focusing on automation, validity and intuition.

  https://www.kdnuggets.com/2019/02/essential-data-science-venn-diagram.html

• What Is Dimension Reduction In Data Science?

  An extensive introduction into Dimension Reduction, including a look at some of the different techniques, linear discriminant analysis, principal component analysis, kernel principal component analysis, and more.

  https://www.kdnuggets.com/2019/01/dimension-reduction-data-science.html

• Data Science Project Flow for Startups

  The aim of this post, then, is to present the characteristic project flow that I have identified in the working process of both my colleagues and myself in recent years. Hopefully, this can help both data scientists and the people working with them to structure data science projects in a way that reflects their uniqueness.

  https://www.kdnuggets.com/2019/01/data-science-project-flow-startups.html

• Logistic Regression: A Concise Technical Overview

  Logistic Regression is a Regression technique that is used when we have a categorical outcome (2 or more categories). Logistic Regression is one of the most easily interpretable classification techniques in a Data Scientist’s portfolio.

  https://www.kdnuggets.com/2019/01/logistic-regression-concise-technical-overview.html

• The Five Best Data Visualization Libraries">The Five Best Data Visualization Libraries

  There are plenty of library options out there to make great visualizations. We outline five of the best, complete with code examples and explanations, that will enable you to create and build interactive visualizations.

  https://www.kdnuggets.com/2019/01/five-best-data-visualization-libraries.html

• Comparison of the Top Speech Processing APIs

  There are two main tasks in speech processing. First one is to transform speech to text. The second is to convert the text into human speech. We will describe the general aspects of each API and then compare their main features in the table.

  https://www.kdnuggets.com/2018/12/activewizards-comparison-speech-processing-apis.html

• BERT: State of the Art NLP Model, Explained

  BERT’s key technical innovation is applying the bidirectional training of Transformer, a popular attention model, to language modelling. It has caused a stir in the Machine Learning community by presenting state-of-the-art results in a wide variety of NLP tasks.

  https://www.kdnuggets.com/2018/12/bert-sota-nlp-model-explained.html

• How to build a data science project from scratch">How to build a data science project from scratch

  A demonstration using an analysis of Berlin rental prices, covering how to extract data from the web and clean it, gaining deeper insights, engineering of features using external APIs, and more.

  https://www.kdnuggets.com/2018/12/build-data-science-project-from-scratch.html

• Top KDnuggets tweets, Nov 21-27: Intro to #DataScience for Managers – a mindmap; An Introduction to #AI

  Also: An Introduction to #AI; Intuitively Understanding Convolutions for #DeepLearning; 10 Free Must-See Courses for Machine Learning and Data Science.

  https://www.kdnuggets.com/2018/11/top-tweets-nov21-27.html

• 8 Reasons to Take Data Analytics Certification Courses

  We outline some of the benefits of taking data analytics classes, including the huge job opportunities, the current gap in the market, the salary aspect, the flexibility of working in any sector, and more.

  https://www.kdnuggets.com/2018/11/8-reasons-take-data-analytics-certification-courses.html

• Top 5 domains Big Data analytics helps to transform

  Big data analytics gives a competitive advantage to companies across many industries, especially, financial services, e-commerce, aviation, transportation, logistics, and energy. It enables to reduce downtime, mitigate risks, cut costs, and improve performance.

  https://www.kdnuggets.com/2018/11/top-5-domains-big-data-analytics.html

• 6 Goals Every Wannabe Data Scientist Should Make for 2019

  Looking to embark on a new path as a data scientist? That goal may be worthy, but it's essential for people to also set goals for 2019 that will help them get closer to that broader aim.

  https://www.kdnuggets.com/2018/11/6-goals-every-wannabe-data-scientist-2019.html

• The 5 Basic Statistics Concepts Data Scientists Need to Know">The 5 Basic Statistics Concepts Data Scientists Need to Know

  Today, we’re going to look at 5 basic statistics concepts that data scientists need to know and how they can be applied most effectively!

  https://www.kdnuggets.com/2018/11/5-basic-statistics-concepts-data-scientists-need-know.html

• Get a 2–6x Speed-up on Your Data Pre-processing with Python

  Get a 2–6x speed-up on your pre-processing with these 3 lines of code!

  https://www.kdnuggets.com/2018/10/get-speed-up-data-pre-processing-python.html

• 5 “Clean Code” Tips That Will Dramatically Improve Your Productivity

  TL;DR: If it isn’t tested, it’s broken; Choose meaningful names; Classes and functions should be small and obey the Single Responsibility Principle (SRP); Catch and handle exceptions, even if you don’t think you need to; Logs, logs, logs

  https://www.kdnuggets.com/2018/10/5-clean-code-tips-dramatically-improve-productivity.html

• How many data scientists are there and is there a shortage?">How many data scientists are there and is there a shortage?

  We examine the famous McKinsey prediction from 2011 and look into whether there a shortage of people with analytical expertise and estimate how many Data Scientists are there.

  https://www.kdnuggets.com/2018/09/how-many-data-scientists-are-there.html

• You Aren’t So Smart: Cognitive Biases are Making Sure of It">You Aren’t So Smart: Cognitive Biases are Making Sure of It

  Cognitive biases are tendencies to think in certain ways that can lead to systematic deviations from a standard of rationality or good judgment. They have all sorts of practical impacts on our lives, whether we want to admit it or not.

  https://www.kdnuggets.com/2018/09/practical-cognitive-biases.html

• The Economics and Benefits of Artificial Intelligence

  In this article, focus on current AI, which is mostly based on the algorithms that can do predictions, and discuss how the economics of AI works and how it may affect business.

  https://www.kdnuggets.com/2018/09/economics-benefits-artificial-intelligence.html

• Comparison of the Most Useful Text Processing APIs">Comparison of the Most Useful Text Processing APIs

  There is a need to compare different APIs to understand key pros and cons they have and when it is better to use one API instead of the other. Let us proceed with the comparison.

  https://www.kdnuggets.com/2018/08/comparison-most-useful-text-processing-apis.html

• Basic Statistics in Python: Probability

  At the most basic level, probability seeks to answer the question, "What is the chance of an event happening?" To calculate the chance of an event happening, we also need to consider all the other events that can occur.

  https://www.kdnuggets.com/2018/08/basic-statistics-python-probability.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

• An Introduction to t-SNE with Python Example

  In this post we’ll give an introduction to the exploratory and visualization t-SNE algorithm. t-SNE is a powerful dimension reduction and visualization technique used on high dimensional data.

  https://www.kdnuggets.com/2018/08/introduction-t-sne-python.html

• Programming Best Practices For Data Science">Programming Best Practices For Data Science

  In this post, I'll go over the two mindsets most people switch between when doing programming work specifically for data science: the prototype mindset and the production mindset.

  https://www.kdnuggets.com/2018/08/programming-best-practices-data-science.html

• 5 reasons data analytics are falling short

  When it comes to big data, possession is not enough. Comprehensive intelligence is the key. But traditional data analytics paradigms simply cannot deliver on the promise of data-driven insights. Here’s why.

  https://www.kdnuggets.com/2018/07/5-reasons-data-analytics-falling-short.html

• How to Build a Data Science Portfolio">How to Build a Data Science Portfolio

  This post will include links to where various data science professionals (data science managers, data scientists, social media icons, or some combination thereof) and others talk about what to have in a portfolio and how to get noticed.

  https://www.kdnuggets.com/2018/07/build-data-science-portfolio.html

• The Future of Map-Making is Open and Powered by Sensors and AI

  This article investigates the future of map-making and the role of Sensors, Artificial Intelligence and Machine Learning within that.

  https://www.kdnuggets.com/2018/07/future-map-making-open-sensors-ai.html

• Text Classification & Embeddings Visualization Using LSTMs, CNNs, and Pre-trained Word Vectors

  In this tutorial, I classify Yelp round-10 review datasets. After processing the review comments, I trained three model in three different ways and obtained three word embeddings.

  https://www.kdnuggets.com/2018/07/text-classification-lstm-cnn-pre-trained-word-vectors.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

• Technical Content Personalization

  Part 3 of this series moves on from segmenting audiences to the technological side of the process.

  https://www.kdnuggets.com/2018/06/technical-content-personalization.html

• Command Line Tricks For Data Scientists

  Aspiring to master the command line should be on every developer’s list, especially data scientists. Learning the ins and outs of your terminal will undeniably make you more productive.

  https://www.kdnuggets.com/2018/06/command-line-tricks-data-scientists.html

• Audience Segmentation

  The process of audience segmentation is not about just statistics, it’s about finding your ideal clients and choosing the right way of interaction with them.

  https://www.kdnuggets.com/2018/06/audience-segmentation.html

• The Future of Artificial Intelligence: Is Your Job Under Threat?

  This article examines the rapid growth of artificial intelligence: how we got to this point, the future AI job market and what can be done.

  https://www.kdnuggets.com/2018/06/future-ai-job-under-threat.html

• Using Linear Regression for Predictive Modeling in R

  In this post, we’ll use linear regression to build a model that predicts cherry tree volume from metrics that are much easier for folks who study trees to measure.

  https://www.kdnuggets.com/2018/06/linear-regression-predictive-modeling-r.html

• Simple Derivatives with PyTorch

  PyTorch includes an automatic differentiation package, autograd, which does the heavy lifting for finding derivatives. This post explores simple derivatives using autograd, outside of neural networks.

  https://www.kdnuggets.com/2018/05/simple-derivatives-pytorch.html

• Top 7 Data Science Use Cases in Finance

  We have prepared a list of data science use cases that have the highest impact on the finance sector. They cover very diverse business aspects from data management to trading strategies, but the common thing for them is the huge prospects to enhance financial solutions.

  https://www.kdnuggets.com/2018/05/top-7-data-science-use-cases-finance.html

• Jupyter Notebook for Beginners: A Tutorial

  The Jupyter Notebook is an incredibly powerful tool for interactively developing and presenting data science projects. Although it is possible to use many different programming languages within Jupyter Notebooks, this article will focus on Python as it is the most common use case.

  https://www.kdnuggets.com/2018/05/jupyter-notebook-beginners-tutorial.html

• Role of IoT in Education

  In this article, I will discuss the significance of IoT and gain insights on why this technology is becoming an integral part of the daily learning and teaching methodologies.

  https://www.kdnuggets.com/2018/04/role-iot-education.html

• Principles of Guided Analytics

  KNIME outline their guided analytics system and explain how this can assist data scientists to predict future outcomes.

  https://www.kdnuggets.com/2018/03/principles-guided-analytics.html

• 5 Things You Need to Know about Sentiment Analysis and Classification">5 Things You Need to Know about Sentiment Analysis and Classification

  We take a look at the important things you need to know about sentiment analysis, including social media, classification, evaluation metrics and how to visualise the results.

  https://www.kdnuggets.com/2018/03/5-things-sentiment-analysis-classification.html

• Quick Feature Engineering with Dates Using fast.ai

  The fast.ai library is a collection of supplementary wrappers for a host of popular machine learning libraries, designed to remove the necessity of writing your own functions to take care of some repetitive tasks in a machine learning workflow.

  https://www.kdnuggets.com/2018/03/feature-engineering-dates-fastai.html

• Web Scraping with Python: Illustration with CIA World Factbook

  In this article, we show how to use Python libraries and HTML parsing to extract useful information from a website and answer some important analytics questions afterwards.

  https://www.kdnuggets.com/2018/03/web-scraping-python-cia-world-factbook.html

• Introduction to Markov Chains">Introduction to Markov Chains

  What are Markov chains, when to use them, and how they work

  https://www.kdnuggets.com/2018/03/introduction-markov-chains.html

• How to Survive Your Data Science Interview

  There are many wonderful things about data science. It’s extreme breadth is not one of them. The title of data scientist means something different at every company

  https://www.kdnuggets.com/2018/03/survive-data-science-interview.html

• A powerful new IDE to build, test, and run Apache Spark applications on your desktop for free!

  Build enterprise-grade functionally rich Spark applications with the aid of an intuitive drag-and-drop user interface and a wide array of pre-built Spark operators.

  https://www.kdnuggets.com/2018/02/impetus-visual-spark-studio.html

• A Comparative Analysis of Top 6 BI and Data Visualization Tools in 2018">A Comparative Analysis of Top 6 BI and Data Visualization Tools in 2018

  In this article, we will compare the most commonly used platforms and analyze their main features to help you choose one or several platforms that will provide indispensable aid for your work communication.

  https://www.kdnuggets.com/2018/02/comparative-analysis-top-6-bi-data-visualization-tools-2018.html

• Calculating Customer Lifetime Value: SQL Example

  In order to understand how to estimate LTV, it is useful to first think about evaluating a customer’s lifetime value at the end of their relationship with us.

  https://www.kdnuggets.com/2018/02/calculating-customer-lifetime-value-sql-example.html

• Web Scraping Tutorial with Python: Tips and Tricks">Web Scraping Tutorial with Python: Tips and Tricks

  This post is intended for people who are interested to know about the common design patterns, pitfalls and rules related to the web scraping.

  https://www.kdnuggets.com/2018/02/web-scraping-tutorial-python.html

• Want to Become a Data Scientist? Try Feynman Technique">Want to Become a Data Scientist? Try Feynman Technique

  Get over the impostor syndrome by developing a strong understanding about the various Data Science topics using the Feynman Technique

  https://www.kdnuggets.com/2018/01/data-scientist-feynman-technique.html