All Blog Posts

← Back to Blog Home

Imported 96 published WordPress posts.

Posting Guidelines

  • Every post should have one clear top-level category.
  • Every post should have tags that help connect it to related writing.
  • Use Photo Travel for visual travel stories and itinerary-style posts.
  • Use Thoughts & Musings for personal essays, reflections, and broader notes.
  • If a post extends earlier work, link back to the previous post.

All Posts (Newest First)

Recent Posts

HowTo - Pose Graph Bundle Adjustment

robotics-perception-systems

SLAM (Simultaneous Localization and Mapping) is one of the important practical areas in computer vision / robotics / image based modelling community. A SLAM system typically consists of a) …

Generating randoms from a specified CDF

math-estimation-optimization

This post deals with generating random numbers given a CDF (Cumulative distribution function). CDF may be specified as an analytical function or as a table of values. We also assume that we …

NetVLAD - Supervised Place Recognition

robotics-perception-systems

Download PPT - Google Docs Vector of locally aggregated descriptors (VLAD) [1] is a simple and popular technique for computing a fingerprint of an image for place recognition. It basically …

Recurrent Neural Net: Memo

ai-ml-inference

RNN (Recurrent Neural nets) are used to model sequences. Unlike the usual feedforward nets which are stateless in terms on inputs, RNNs have memory. In particular, its inputs are the output …

Generative Networks : Memo

ai-ml-inference

Ian Goodfellow’s one of the popular works is the GAN (Generative Adversarial Networks). These networks basically can generate images (which look like real images). In the coming …

Soft Indicator Function

robotics-perception-systems

Very often we come across indicator functions denoting class membership. These functions in their native form are neither continuous nor differentiable. I will describe a trick to convert …

Reinforcement Learning : Memo

ai-ml-inference

I came across this tutorial series on Reinforcement Learning by Arthur Juliani: [WWW] Fundamentals textbook : Reinforcement Learning: An Introduction - By Richard S. Sutton and Andrew G. …

Convolutional Networks

ai-ml-inference

Continuing further with Deep Learning, here I will briefly describe what I learned on convolutional network (CNN). If you understand the basics of a simple 2-layer network (fully connected) …

Sending Email from Terminal using mutt

systems-engineering-tooling

Often times one deals with long running programs and need a quick way to know when the program is finished or intermediate reporting. Simplest way is to email yourself the progress say …

Deep Residual Nets with Tensorflow

ai-ml-inference

Git Gist : https://gist.github.com/mpkuse/6f9dcd419effa707422eb2c5097f51b4 Deep Residual Nets (ResNets) from Microsoft Research has become one of the popular deep learning network …

Toy Kernels

ai-ml-inference

There is a whole lot of literature on mapping data onto higher dimensional spaces. Another closely related and popular term is the kernel trick. See top publications of Prof. Bernhard …

Robust Keypoint Point Matching

robotics-perception-systems

Came across this interesting paper which does feature matching (SIFT-like features) between images under a probabilistic formulation. The methods starts with all matches as inliers and as …