Mar
2017 Apr Tutorials, Overviews
http likes 170All (110) | Courses, Education (8) | Meetings (19) | News, Features (23) | Opinions, Interviews (21) | Software (3) | Tutorials, Overviews (28) | Webcasts & Webinars (8)
-
Keep it simple! How to understand Gradient Descent algorithm - Apr 28, 2017.
In Data Science, Gradient Descent is one of the important and difficult concepts. Here we explain this concept with an example, in a very simple way. Check this out. - One Deep Learning Virtual Machine to Rule Them All - Apr 28, 2017.
The frontend code of programming languages only needs to parse and translate source code to an intermediate representation (IR). Deep Learning frameworks will eventually need their own “IR.”
- Models: From the Lab to the Factory - Apr 27, 2017.
In this post, we’ll go over techniques to avoid these scenarios through the process of model management and deployment.
- Dask and Pandas and XGBoost: Playing nicely between distributed systems - Apr 27, 2017.
This blogpost gives a quick example using Dask.dataframe to do distributed Pandas data wrangling, then using a new dask-xgboost package to setup an XGBoost cluster inside the Dask cluster and perform the handoff.
- How to Build a Recurrent Neural Network in TensorFlow - Apr 26, 2017.
This is a no-nonsense overview of implementing a recurrent neural network (RNN) in TensorFlow. Both theory and practice are covered concisely, and the end result is running TensorFlow RNN code.
- Must-Know: When can parallelism make your algorithms run faster? When could it make your algorithms run slower? - Apr 25, 2017.
Efficient implementation is key to achieving the benefits of parallelization, even though parallelism is a good idea when the task can be divided into sub-tasks that can be executed independent of each other without communication or shared resources.
- Data Science Dividends – A Gentle Introduction to Financial Data Analysis - Apr 24, 2017.
This post outlines some very basic methods for performing financial data analysis using Python, Pandas, and Matplotlib, focusing mainly on stock price data. A good place for beginners to start.
- Difference Between Big Data and Internet of Things - Apr 21, 2017.
If you cannot manage real-time streaming data and make real-time analytics and real-time decisions at the edge, then you are not doing IOT or IOT analytics, in my humble opinion. So what is required to support these IOT data management and analytic requirements?
-
Awesome Deep Learning: Most Cited Deep Learning Papers - Apr 21, 2017.
This post introduces a curated list of the most cited deep learning papers (since 2012), provides the inclusion criteria, shares a few entry examples, and points to the full listing for those interested in investigating further. - The Value of Exploratory Data Analysis - Apr 20, 2017.
In this post, we will give a high level overview of what exploratory data analysis (EDA) typically entails and then describe three of the major ways EDA is critical to successfully model and interpret its results.
- Negative Results on Negative Images: Major Flaw in Deep Learning? - Apr 20, 2017.
This is an overview of recent research outlining the limitations of the capabilities of image recognition using deep neural networks. But should this really be considered a "limitation?"
- Time Series Analysis with Generalized Additive Models - Apr 18, 2017.
In this tutorial, we will see an example of how a Generative Additive Model (GAM) is used, learn how functions in a GAM are identified through backfitting, and learn how to validate a time series model.
- Must-Know: What is the curse of dimensionality? - Apr 18, 2017.
What is the curse of dimensionality? This post gives a no-nonsense overview of the concept, plain and simple.
- Predictive Maintenance: A Primer - Apr 17, 2017.
Companies can no longer afford to have product rollbacks or have wastage because of replacement parts. This is where the need for “Predictive Maintenance” comes into play.
-
New Online Data Science Tracks for 2017 - Apr 17, 2017.
In 2017 there are many new and revamped data science tracks that are much more comprehensive for beginners than ever before. The tracks are designed to give you the skills you need to grab a job in data science, and some even have a job guarantee. - Is Blockchain the Ultimate Enabler of Data Monetization? - Apr 14, 2017.
Is blockchain the ultimate enabler of data and analytics monetization; creating marketplaces where companies, individuals and even smart entities (cars, trucks, building, airports, malls) can share/sell/trade/barter their data and analytic insights directly with others?
- Medical Image Analysis with Deep Learning , Part 2 - Apr 13, 2017.
In this article we will talk about basics of deep learning from the lens of Convolutional Neural Nets. We plan to use this knowledge to build CNNs in the next post and use Keras to develop a model to predict lung cancer.
- 5 Machine Learning Projects You Can No Longer Overlook, April - Apr 13, 2017.
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.
- Machine Learning Finds “Fake News” with 88% Accuracy - Apr 12, 2017.
In this post, the author assembles a dataset of fake and real news and employs a Naive Bayes classifier in order to create a model to classify an article as fake or real based on its words and phrases.
- Anonymization and the Future of Data Science - Apr 11, 2017.
This post walks the reader through a real-world example of a "linkage" attack to demonstrate the limits of data anonymization. New privacy regulation, most notably the GDPR, are making it increasingly difficult to maintain a balance between privacy and utility.
- Must-Know: How to evaluate a binary classifier - Apr 11, 2017.
Binary classification is a basic concept which involves classifying the data into two groups. Read on for some additional insight and approaches.
- The 42 V’s of Big Data and Data Science - Apr 7, 2017.
It's 2017 now, and we now operate in an ever more sophisticated world of analytics. To keep up with the times, we present our updated 2017 list: The 42 V's of Big Data and Data Science.
- A Brief History of Artificial Intelligence - Apr 7, 2017.
This post is a brief outline of what happened in artificial intelligence in the last 60 years. A great place to start or brush up on your history.
- Top 20 Recent Research Papers on Machine Learning and Deep Learning - Apr 6, 2017.
Machine learning and Deep Learning research advances are transforming our technology. Here are the 20 most important (most-cited) scientific papers that have been published since 2014, starting with "Dropout: a simple way to prevent neural networks from overfitting".
- Finding “Gems” in Big Data - Apr 4, 2017.
Detecting anomalous cases in large datasets is critical in conducting surveillance, countering credit-card fraud, protecting against network hacking, combating insurance fraud, and many more applications in government, business and healthcare. Learn how to do it online in "Anomaly Detection" course at Statistics.com.
- Must-Know: Why it may be better to have fewer predictors in Machine Learning models? - Apr 4, 2017.
There are a few reasons why it might be a better idea to have fewer predictor variables rather than having many of them. Read on to find out more.
- Introduction to Anomaly Detection - Apr 3, 2017.
This overview will cover several methods of detecting anomalies, as well as how to build a detector in Python using simple moving average (SMA) or low-pass filter.
- What is AI? Ingredients for Intelligence - Apr 3, 2017.
This introductory overview of artificial intelligence acts as a layman's guide what AI is, and what it is made up of.
Interpretable Machine Learning: The Free eBook