-
Building, Training, and Improving on Existing Recurrent Neural Networks
In this post, we’ll provide a short tutorial for training a RNN for speech recognition, including code snippets throughout.
-
Do We Need Balanced Sampling?
Resampling is a solution which is very popular in dealing with class imbalance. Our research on churn prediction shows that balanced sampling is unnecessary.
-
How to Fail with Artificial Intelligence: 9 creative ways to make your AI startup fail
This post summarizes nine creative ways to condemn almost any AI startup to bankruptcy. I focus on data science and machine learning startups, but the lessons on what to avoid can easily be applied to other industries.
-
The 2017 Data Scientist Report is now available
For the third year in a row, CrowdFlower surveyed data scientists (nearly 200 this year) from all manner of organizations, which they have compiled into one free report which you can be downloaded now. This year, lots of insights into the word of AI are included.
-
Models: From the Lab to the Factory
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
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
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.
-
AI & Machine Learning Black Boxes: The Need for Transparency and Accountability
When something goes wrong, as it inevitably does, it can be a daunting task discovering the behavior that caused an event that is locked away inside a black box where discoverability is virtually impossible.
-
 Awesome Deep Learning: Most Cited Deep Learning Papers
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
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.
|
Awesome Deep Learning: Most Cited Deep Learning Papers