Deriving the Softmax from First Principles
April 19, 2017
—

Will Wolf
Deriving the softmax from first conditional probabilistic principles, and how this framework extends naturally to define the softmax regression, conditional random fields, naive Bayes and hidden Markov models.

Approximating Implicit Matrix Factorization with Shallow Neural Networks
April 7, 2017
—

Will Wolf
In this post, we look to beat the performance of Implicit Matrix Factorization on a recommendation task using 5 different neural network architectures.

Intercausal Reasoning in Bayesian Networks
March 13, 2017
—

Will Wolf
Simple intercausal reasoning on a 3-node Bayesian network.

Bayesian Inference via Simulated Annealing
February 7, 2017
—

Will Wolf
A toy, hand-rolled Bayesian model, optimized via simulated annealing.

RescueTime Inference via the "Poor Man's Dirichlet"
February 3, 2017
—

Will Wolf
Modeling a typical week of RescueTime data via an alternative take on the Dirichlet distribution.

Generating World Flags with Sparse Auto-Encoders
December 13, 2016
—

Will Wolf
Hand-rolled sparse autoencoders to generate novel world flags.

Docker and Kaggle with Ernie and Bert
November 22, 2016
—

Will Wolf
An introduction to what Docker is and why and how to use it for Kaggle.

While We Were Busy with Prosperity
November 10, 2016
—

Will Wolf
Some whirling thoughts on the Trump election.

Recurrent Neural Network Gradients, and Lessons Learned Therein
October 18, 2016
—

Will Wolf
Recurrent neural network gradients by hand.