2019 Apr Tutorials, Overviews
All (109) | Courses, Education (11) | Meetings (15) | News (13) | Opinions (30) | Top Stories, Tweets (10) | Tutorials, Overviews (27) | Webcasts & Webinars (3)
- Naive Bayes: A Baseline Model for Machine Learning Classification Performance - May 7, 2019.
We can use Pandas to conduct Bayes Theorem and Scikitlearn to implement the Naive Bayes Algorithm. We take a step by step approach to understand Bayes and implementing the different options in Scikitlearn.
- Normalization vs Standardization — Quantitative analysis - Apr 30, 2019.
Stop using StandardScaler from Sklearn as a default feature scaling method can get you a boost of 7% in accuracy, even when you hyperparameters are tuned!
- Pandas DataFrame Indexing - Apr 29, 2019.
The goal of this post is identify a single strategy for pulling data from a DataFrame using the Pandas Python library that is straightforward to interpret and produces reliable results.
- Graduating in GANs: Going From Understanding Generative Adversarial Networks to Running Your Own - Apr 25, 2019.
Read how generative adversarial networks (GANs) research and evaluation has developed then implement your own GAN to generate handwritten digits.
- Generative Adversarial Networks – Key Milestones and State of the Art - Apr 24, 2019.
We provide an overview of Generative Adversarial Networks (GANs), discuss challenges in GANs learning, and examine two promising GANs: the RadialGAN, designed for numbers, and the StyleGAN, which does style transfer for images.
- Attention Craving RNNS: Building Up To Transformer Networks - Apr 24, 2019.
RNNs let us model sequences in neural networks. While there are other ways of modeling sequences, RNNs are particularly useful. RNNs come in two flavors, LSTMs (Hochreiter et al, 1997) and GRUs (Cho et al, 2014)
- 2019 Best Masters in Data Science and Analytics – Online - Apr 23, 2019.
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.
- Approach pre-trained deep learning models with caution - Apr 23, 2019.
Pre-trained models are easy to use, but are you glossing over details that could impact your model performance?
- The Mueller Report Word Cloud: A brief tutorial in R - Apr 22, 2019.
Word clouds are simple visual summaries of the mostly frequently used words in a text, presenting essentially the same information as a histogram but are somewhat less precise and vastly more eye-catching. Get a quick sense of the themes in the recently released Mueller Report and its 448 pages of legal content.
- Data Visualization in Python: Matplotlib vs Seaborn - Apr 19, 2019.
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.
- How Optimization Works - Apr 18, 2019.
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.
- Best Data Visualization Techniques for small and large data - Apr 17, 2019.
Data visualization is used in many areas to model complex events and visualize phenomena that cannot be observed directly, such as weather patterns, medical conditions or mathematical relationships. Here we review basic data visualization tools and techniques.
- Building a Flask API to Automatically Extract Named Entities Using SpaCy - Apr 17, 2019.
This article discusses how to use the Named Entity Recognition module in spaCy to identify people, organizations, or locations in text, then deploy a Python API with Flask.
- How Machines Make Sense of Big Data: an Introduction to Clustering Algorithms - Apr 16, 2019.
We outline three different clustering algorithms - k-means clustering, hierarchical clustering and Graph Community Detection - providing an explanation on when to use each, how they work and a worked example.
- 2019 Best Masters in Data Science and Analytics – Europe Edition - Apr 16, 2019.
We provide an updated list of our comprehensive, unbiased survey of graduate programs in Data Science and Analytics from across Europe.
- Data Science with Optimus Part 2: Setting your DataOps Environment - Apr 16, 2019.
Breaking down data science with Python, Spark and Optimus. Today: Data Operations for Data Science. Here we’ll learn to set-up Git, Travis CI and DVC for our project.
- An introduction to explainable AI, and why we need it - Apr 15, 2019.
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.
- Data Science with Optimus Part 1: Intro - Apr 15, 2019.
With Optimus you can clean your data, prepare it, analyze it, create profilers and plots, and perform machine learning and deep learning, all in a distributed fashion, because on the back-end we have Spark, TensorFlow, Sparkling Water and Keras. It’s super easy to use.
- AI For Ordinary Folks - Apr 11, 2019.
There are many excellent books, articles, YouTube lectures and blogs on AI and topics related to it aimed at data scientists and AI researchers. You may want to, instead, check out this list of AI resources crafted for ordinary folks.
- All you need to know about text preprocessing for NLP and Machine Learning - Apr 9, 2019.
We present a comprehensive introduction to text preprocessing, covering the different techniques including stemming, lemmatization, noise removal, normalization, with examples and explanations into when you should use each of them.
- Advanced Keras — Constructing Complex Custom Losses and Metrics - Apr 8, 2019.
In this tutorial I cover a simple trick that will allow you to construct custom loss functions in Keras which can receive arguments other than
- Another 10 Free Must-See Courses for Machine Learning and Data Science - Apr 5, 2019.
Check out another follow-up collection of free machine learning and data science courses to give you some spring study ideas.
- Building a Recommender System - Apr 4, 2019.
A beginners guide to building a recommendation system, with a step-by-step guide on how to create a content-based filtering system to recommend movies for a user to watch.
- Predict Age and Gender Using Convolutional Neural Network and OpenCV - Apr 4, 2019.
Age and gender estimation from a single face image are important tasks in intelligent applications. As such, let's build a simple age and gender detection model in this detailed article.
- Getting started with NLP using the PyTorch framework - Apr 3, 2019.
We discuss the classes that PyTorch provides for helping with Natural Language Processing (NLP) and how they can be used for related tasks using recurrent layers.
- Top 8 Data Science Use Cases in Gaming - Apr 3, 2019.
The understanding of the data value for optimization and improvement of gaming makes specialists search for new ways to apply data science and its benefits in the gaming business. Therefore, various specific data science use cases appear. Here is our list of the most efficient and widely applied data science use cases in gaming.
- Which Face is Real? - Apr 2, 2019.
Which Face Is Real? was developed based on Generative Adversarial Networks as a web application in which users can select which image they believe is a true person and which was synthetically generated. The person in the synthetically generated photo does not exist.