Efficiently Computing the Fisher Vector Product in TRPO
The purpose of this post is to provide math proofs and clarify some implementation details in the recently introduced reinforcement learning method called “Trust Region […]
Code
Calculating the Derivative of the Error with respect to Convolution Filter Weights in a CNN
Over the last month, I have been exploring the world of deep learning. Deep learning based algorithms have been around for a long time, but […]
Calculating Position from Raw GPS Data
We are all familiar with GPS (Global Positioning System) and its myriad applications. From getting directions using Google maps to hailing a ride using a ride sharing […]
Sensor Fusion: Part 4
In this post, we’ll add the math and provide implementation for adding image based measurements. Let’s recap the notation and geometry first introduced in part […]
Sensor Fusion – Part 3: Implementation of Gyro-Accel Sensor Fusion
In the previous posts, we laid the mathematical foundation necessary for implementing the error state kalman filter. In this post, we’ll provide the Matlab implementation […]
Sensor Fusion: Part 2 (combining Gyro-Accel data)
In the previous post, we laid some of the mathematical foundation behind the kalman filter. In this post, we’ll look at our first concrete example […]
Sensor Fusion: Part 1
In this series of posts, I’ll provide the mathematical derivations, implementation details and my own insights for the sensor fusion algorithm described in 1. This paper describes a […]