greydanus Goto Github PK
Name: Sam
Type: User
Bio: Windscape AI and Greenfield Properties. Previously @Google Brain, @Dartmouth College
Twitter: samgreydanus
Name: Sam
Type: User
Bio: Windscape AI and Greenfield Properties. Previously @Google Brain, @Dartmouth College
Twitter: samgreydanus
The idea here was to teach an RNN to draw, pixel by pixel, over a template image using DDPG
A high-performance Atari A3C agent in 180 lines of PyTorch
Simple MNIST baselines for 1) numpy backprop 2) dense nns 3) cnns 3) seq2seq
A simple RL environment for studying planning.
Exploring the quantum nature of light with compton scattering
Learning the Enigma with Recurrent Neural Networks
Training a transformer to generate cursive
Use a pretrained NLP model to rank thesaurus suggestions
Fork from Sosanya's GitHub of our code for "Dissipative HNNs"
Forays into the world of deep learning using TensorFlow
Differentiable Neural Computer in TensorFlow
A minimal evolution strategies benchmark
Visualizing how deep networks make decisions
A numerical model of fractal dynamics
Exploring social behavior with qLearning agents
A repo for hosting a generic Heroku app
My academic blog
Code for our paper "Hamiltonian Neural Networks"
my blog
Fork of codebase from Miles Cranmer's GitHub
import numpy as np and enjoy
Generative Adversarial Networks for the MNIST dataset
A 1D analogue of the MNIST dataset for measuring spatial biases and answering Science of Deep Learning questions.
A LSTM recurrent neural network implemented in pure numpy
Nature's Cost Function (NCF). Finding paths of least action with gradient descent.
Neural reparameterization improves structural optimization
Neural network experiments written purely in numpy
We simulate a wind tunnel, place a rectangular occlusion in it, and then use gradient descent to turn the occlusion into a wing.
Paper reviews for my work with the XAI group at Oregon State
Code for "Proximal Distilled Evolutionary Reinforcement Learning", accepted at AAAI 2020
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.