• Neural Nets - Part 1: Perceptrons

    Over the past decade or so, neural networks have shown amazing success across a wide variety of tasks. In this post, I'll introduce the grandfather of modern neural networks: the perceptron.
  • Language Modeling - Part 2: Embeddings

    Moving beyond n-grams, embeddings let us better represent the meaning of words and quantify their relationships to other words.
  • Language Modeling - Part 1: n-gram Models

    We'll start our language modeling journey starting at classical language modeling using n-gram language models.
  • Lie Groups - Part 2

    I'll continue the discussion of Lie Groups into the realm of calculus on Lie Groups; we'll finish applying them to the robotic state estimation.
  • Lie Groups - Part 1

    I'll introduce concept of Lie Groups and how they can be useful for working with constrained surfaces like rotations; we'll also apply them to the problem of accurate robotic state estimation.
  • Manifolds - Part 3

    In the last part, I'll show how we can define curvature on a manifold by extending calculus to work on manifolds with the covariant derivative!
  • Manifolds - Part 2

    In the second part, I'll construct a manifold from scratch and redefine vectors, dual vectors, and tensors on a manifold.
  • Manifolds - Part 1

    As the first in a multi-part series, I'll introduce manifolds and discuss how vectors, dual vectors, and tensors work in a flat, Euclidean space.
  • Particle Filters for Robotic State Estimation

    Going beyond EKFs, I'll motivate particle filters as a more advanced state estimator that can compensate for the limitations of EKFs.
  • Extended Kalman Filtering for Robotic State Estimation

    I discuss a fundamental building block for state estimation for a robot: the extended kalman filter (EKF).
  • Deep Reinforcement Learning: Policy-based Methods

    I discuss state-of-the-art deep RL techniques that use policy-based methods.
  • Deep Reinforcement Learning: Value-based Methods

    I overview some of the fundamental deep reinforcement learning algorithms used as the basis for many of the more advanced techniques used in practice and research.
  • Reinforcement Learning

    I describe the fundamental algorithms and techniques used in reinforcement learning.
  • Undergraduate Research

    I chronicle some lessons learned from my 2.5 years as an undergrad student researcher.
  • Sequence-to-Sequence Models

    I discuss the magic behind attention-based sequence-to-sequence models, the very same models used in tasks such as machine translation.
  • Undergraduate Tips and Tricks

    After finishing finish my undergrad, I'll share some pointers (pun absolutely intended) that I've learned over the past few years.
  • Restricted Boltzmann Machines

    I'll explain one of the more difficult unsupervised neural networks in detail using examples and intuition.
  • Understanding Backpropagation

    I'll discuss the backpropagation algorithm on various levels using concrete examples.
  • Depth Perception: The Next Big Thing in Computer Vision

    Devices like the HoloLens and Tango have depth-sensing capabilities, allowing for a completely different level of augmented reality.