brain-research/wip-lambada-lm

This repository has been archived on 27/Jul/2022
Stars
9
Rank 1,929,501 (Top 39 %)
Language
Python
License
Apache License 2.0
Created almost 8 years ago
Updated almost 8 years ago

brain-research/wip-lambada-lm

brain-research

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

LSTM language model on LAMBADA dataset

self-attention-gan

realistic-ssl-evaluation

Open source release of the evaluation benchmark suite described in "Realistic Evaluation of Deep Semi-Supervised Learning Algorithms"

guided-evolutionary-strategies

Guided Evolutionary Strategies

Jupyter Notebook

acai

Code for "Understanding and Improving Interpolation in Autoencoders via an Adversarial Regularizer"

mpnn

Open source implementation of "Neural Message Passing for Quantum Chemistry"

tensorfuzz

A library for performing coverage guided fuzzing of neural networks

nngp

Deep neural network kernel for Gaussian process

l2hmc

TensorFlow implementation for training MCMC samplers from the paper: Generalizing Hamiltonian Monte Carlo with Neural Network

Jupyter Notebook

deep-molecular-massspec

Mass Spectrometry for Small Molecules using Deep Learning

long-term-video-prediction-without-supervision

Implementation of Hierarchical Long-term Video Prediction without Supervision

data-linter

The Data Linter identifies potential issues (lints) in your ML training data.

conv-sv

The Singular Values of Convolutional Layers

ncp

Reliable Uncertainty Estimates in Deep Neural Networks using Noise Contrastive Priors

mean-field-cnns

Jupyter Notebook

mirage-rl

Code to reproduce the experiments in The Mirage of Action-Dependent Baselines in Reinforcement Learning.

LeaveNoTrace

Leave No Trace is an algorithm for safe reinforcement learning.

fisher-rao-regularization

hyperbolictext

TensorFlow source code for learning embeddings of text sequences in an unsupervised manner.

wip-constrained-extractor

Work in progress inference, learning, and evaluation code for extractive summarization.

flying-shapes

A potentially infinite dataset of coloured shapes which bounce around on a black background.

metaq