Open in app
Home
Notifications
Lists
Stories

Write
Tim Sullivan
Tim Sullivan

Home

About

Published in Towards Data Science

·Pinned

GANs from scratch

Dueling neural networks — Neural networks aren’t limited to just learning data; they can also learn to create it. One of the classic machine learning papers is Generative Adversarial Networks (GANs) (2014) by Ian J. Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, and others. …

Machine Learning

5 min read

GANs from scratch
GANs from scratch

Published in Towards Data Science

·Jun 20, 2021

The Transformer

Working through attention in deep learning — I’ve started to go through classic papers in machine learning, inventions that shifted the state of the art or created an entirely new application. These are my notes on the Transformer introduced in Attention is All You Need. …

Machine Learning

5 min read

The Transformer
The Transformer

Published in Towards Data Science

·Jul 7, 2020

Obama debates Trump

An AI alternative history with natural language processing — My top priority is to reduce carbon emissions. The more we can reduce our dependence on foreign oil, the more energy we can produce. This is why I want the U.S. to keep growing as fast as possible, to do whatever it takes to bring about the transformation of our…

Machine Learning

11 min read

Obama debates Trump
Obama debates Trump

Published in The Startup

·Jun 16, 2020

Introduction to LSTMs and neural network text generation

In my last article on RNNs, we looked at how the purpose of RNNs, how an RNN cell is built, and how to implement RNNs in PyTorch for sequence prediction. …

Machine Learning

12 min read

Introduction to LSTMs and neural network text generation
Introduction to LSTMs and neural network text generation

Published in The Startup

·May 25, 2020

Introduction to recurrent neural networks (RNNs)

Neural networks with memory — Introduction A typical feed-forward neural network maps inputs to outputs with no consideration of previous computations or where the current input fits in relation to others. The network applies the same function to each input regardless of sequence. This is fine for many applications, but often the context of an input…

Machine Learning

6 min read

Introduction to recurrent neural networks (RNNs)
Introduction to recurrent neural networks (RNNs)
Tim Sullivan

Tim Sullivan

sullivantm.com

Following
  • TDS Editors

    TDS Editors

  • MIT IDE Paula Klein, Editor

    MIT IDE Paula Klein, Editor

  • Ryan Holiday

    Ryan Holiday

  • Russ Roberts

    Russ Roberts

  • Santa Fe Institute

    Santa Fe Institute

Help

Status

Writers

Blog

Careers

Privacy

Terms

About

Knowable