Anil Keshwani

Anil Keshwani

Senior Machine Learning Engineer
ai-coustics


Blog

Notes on machine learning. Browse by tag or subscribe via RSS.

  1. Some Information Theory
    information theory

    Sketches of some concepts from Information Theory. Readers are referred to Shannon's original 1948 paper A Mathematical Theory of Communication.

  2. The Hierarchical Softmax
    nlpdeep learning

    The Hierarchical Softmax is useful for efficient classification as it has logarithmic time complexity in the number of output classes, log(N) for N output classes.

  3. CPC: Representation Learning with Contrastive Predictive Coding
    self-supervised learningspeech

    Notes on Representation Learning with Contrastive Predictive Coding (CPC) by Aaron van den Oord, Yazhe Li and Oriol Vinyals.

  4. Self-Supervised Visual Representation Learning
    self-supervised learningcomputer vision

    This post consolidates several literature summaries from the field of self-supervised visual representation learning.

  5. Four Early Lessons from Working on Machine Learning Projects
    engineering

    Some high-level reflections from working on a Computer Vision project in PyTorch.

  6. The Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
    reading groupcomputer vision

    I discussed the Swin Transformer: Hierarchical Vision Transformer using Shifted Windows by Ze Liu and colleagues published at ICCV '21 at the PINLab Reading Group on the 3d November 2021.

  7. LSTMs + Grammar as a Foreign Language
    nlpdeep learning

    A short explanation of long short-term memory networks (LSTMs), a form of recurrent neural network (RNN) and a breakdown of Vinyals et al.

  8. Generalized Linear Models and the Exponential Family
    statistics

    An introduction to the Exponential Family of probability distributions.

  9. Mean, Median and Mode as Representatives
    statistics

    This brief post discusses the underlying basis of the three measures of central tendency that we typically use to represent a distribution, sample or population: the mean, median and mode, prompted by a passing comment made by my Bayesian statistics professor.

  10. Bayes: Conjugate Inference
    statisticsbayesian inference

    Bayesian inference for the cases when the data generating process allows for a conjugate setup.

  11. Graphs: Community Structure
    graphs

    We define modularity, Q, as a measure of how well a network is partitioned into communities.

  12. Graphs: Motifs, Graphlets and Structural Roles in Networks
    graphs

    Networks and nodes can be characterised and compared by finding and profiling their network motifs (subgraphs), specifically induced subgraphs and graphlets (connected subgraphs).

  13. Jabri, Owens and Efros (2020) Space-Time Correspondence as a Contrastive Random Walk
    reading groupself-supervised learningcomputer vision

    I discussed Jabri, Owens and Efros (2020) Space-Time Correspondence as a Contrastive Random Walk published at NeurIPS at the March 31st session of the PINLab Reading Group.

  14. The Probability Distributions
    statistics

    This post introduces a few of the most commonly encountered families of probability distributions: the Poisson, which models rates, and the geometric distribution, which models waiting times for discrete stochastic processes and the exponential, which is a continuous analogue of the geometric relating closely to the Poisson family.

  15. An Evolutionary Perspective on Language
    biologylinguistics

    In this post, I look at some aspects of human language that are claimed to be unique to our linguistic communication, as opposed to existing in some analogue or homologue form in the systems that other animals use to communicate.

  16. Animal Navigation Systems
    biology

    Animals display an amazingly reliable, accurate and sometimes mysterious capacity to navigate.