Thoughts and Theory

Photo by Uriel SC on Unsplash

Motivation: Comparing State-of-the-Art

Deep Neural Networks (DNNs) and Gaussian Processes (GPs)* are two highly expressive classes of supervised learning algorithms. A natural question that comes up when considering the applications of these methodologies: “When and why does it make sense to use one algorithm over the other?”

Thoughts and Theory

Gaussian Process Regression is a remarkably powerful class of machine learning algorithms. Here, we introduce them from first principles.

Gaussian Process Regression (GPR) is a remarkably powerful class of machine learning algorithms that, in contrast to many of today’s state-of-the-art machine learning models, relies on few parameters to make predictions. Because GPR is (almost) non-parametric, it can be applied effectively to solve a wide variety of supervised learning problems…

Getting Started

In this article, we explore how we can, and do, regularize and control the complexity of the models we learn through Bayesian prior beliefs.

I’m currently reading “How We Learn” by Stanislas Dehaene. First off, I cannot recommend this book enough to anyone interested in learning, teaching, or AI.

One of the main themes of this book is explaining the neurological and psychological bases of why humans are so good at learning things quickly…

These quick reviews are designed to expose readers to novel machine learning techniques that I come across. Enjoy :)

Photo by Ricardo Gomez Angel on Unsplash

Overview

Year Published: 2019 (ICML)

Topics covered: data augmentation, deep learning, autoencoders, generalization

Research Gap Filled: Improved the generative capabilities of neural network and autoencoder models through: (i) Randomized Mixup interpolation, (ii)…

Thoughts and Theory

Gaussian Process Regression can be used to learn a multitude of periodic and aperiodic signals, such as those depicted in this figure. Photo by Ryan Stone on Unsplash

Unlimited Model Expression + Modern Computing

Ever wonder how you can create non-parametric supervised learning models with unlimited expressive power? Look no further than Gaussian Process Regression (GPR), an algorithm that learns to make predictions almost entirely from the data itself (with a little help from hyperparameters). …

Making Sense of Big Data

Photo by Jason Leung on Unsplash

Despite recent incredible algorithmic advances in the field, deep reinforcement learning (DRL) remains notorious for being computationally expensive, prone to “silent bugs”, and difficult to tune hyperparameters. These phenomena make running high-fidelity, scientifically-rigorous reinforcement learning experiments paramount.

In this article, I will discuss a few tips and lessons I’ve learned…

Recent advances in TensorFlow and reinforcement learning environments, such as those available through OpenAI Gym and the DeepMind Control Suite, have allowed for rapid prototyping, experimentation, and deployment of reinforcement learning applications across many domains.

TensorFlow-Agents, a TensorFlow-2-based reinforcement learning framework, is a high-level API for training and evaluating a…

Ryan Sander

Image Scientist, MIT CSAIL Alum, Tutor, Dark Roast Coffee Fan, GitHub: https://github.com/rmsander/

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store