Expected Calibration Error
Jan 20, 2020

ECE quantifies how much you can trust the class confidences your model gives. It is the difference between the predicted confidence and reality.

Gradient Through Concatenation
Jul 23, 2019

Concatenation of vector is a common operation in computational graph of modern day Deep Learning Networks. This post describes how to compute derivative of the...

Gradient Through Addition with broadcasting
Sep 18, 2018

Calculating gradient across an addition op is considered a simple algebra trick. But addition of tensors in real applications allow broadcasting. In this post, we...

Softmax Classifier
Mar 28, 2018

Imagine we have a dataset ${x,y}_{i=0}^m$ where $x$ is a data point and $y$ indicates the class $x$ belongs to. For deriving LDA classifier, we...

Linear Classifiers
Feb 18, 2018

In the post on bayes error, we discussed what is the best classifier if the features are not enough to tell the class apart. We...

Differentiable Computations
Feb 18, 2018

Auto gradient is a nice feature found in many computational frameworks. Specify the computation in forward direction and the framework computes backward gradients. Let’s talk...

Bayes Error
Feb 11, 2018

In an ideal world, everything has reason. Every question has a unambiguous answer. The data in sufficient to explain its behaviours, like the class it...