• Stars
    star
    88
  • Rank 375,465 (Top 8 %)
  • Language
    Jupyter Notebook
  • License
    Apache License 2.0
  • Created about 5 years ago
  • Updated 9 months ago

Reviews

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

Repository Details

implementing "recurrent attentive neural processes" to forecast power usage (w. LSTM baseline, MCDropout)

More Repositories

1

rl-portfolio-management

Attempting to replicate "A Deep Reinforcement Learning Framework for the Financial Portfolio Management Problem" https://arxiv.org/abs/1706.10059 (and an openai gym environment)
Jupyter Notebook
540
star
2

keywordshitter2

A website to find long-tail keywords using search suggestions
CSS
168
star
3

viz_torch_optim

Videos of deep learning optimizers moving on 3D problem-landscapes
Jupyter Notebook
105
star
4

world-models-sonic-pytorch

Attempt at reinforcement learning with curiosity for Sonic the Hedgehog games. Number 149 on OpenAI retro contest leaderboard, but more work needed
Jupyter Notebook
31
star
5

satellite_leak_detection

Detect water leaks from satellite images using machine learning
Jupyter Notebook
22
star
6

pipe-segmentation

Using machine learning to find water pipelines in aerial images with 73% accuracy
Jupyter Notebook
20
star
7

phoneme2grapheme

Teaching machines to spell with deep learning (acc=>80%) e.g. a model hears "pɹˈaʊd˺ɚ" and writes "prowder" (but it should be "prouder")
Jupyter Notebook
19
star
8

rl_2d_walker.js

Teaching a humanoid to walk(ish), then displaying in your browser (using tensorflow.js and reinforcement learning)
Jupyter Notebook
10
star
9

compare_altcoin_development

Compare development stats between altcoins
JavaScript
10
star
10

seq2seq-time

Bechmarking seq2seq models on a range of multivariate regression datasets
Jupyter Notebook
8
star
11

valuations_of_ethereum

5
star
12

ascii2segy

This script uses segpy to convert ascii files to segy
Python
4
star
13

awesome-rlhf

Lists of datasets, training, and evals for RLHF and similar
4
star
14

Phonetic_english

Fork of PIE - Phonetically Intuitive English (PIE), to make it compatible with other respelling schemes, primarily Wikipedia's excellent one.
JavaScript
4
star
15

simple_gpt2_chatbot

Jupyter Notebook
3
star
16

svg2cube

Generate isometric game sprites. Inputs an svg panel and it's folded into a cube and rendered from any angle.
JavaScript
3
star
17

awesome-interpretability

Awesome tools for interpreting, manipulating the internals of of deep neural networks.
3
star
18

detect_bs_text

Can we measure how good a text is by how much an LLM learns from it?
Jupyter Notebook
2
star
19

adapters_can_monitor_lies

inspired by circuit breakers paper. honesty>harmless
Jupyter Notebook
2
star
20

open_pref_eval

Hackable, simple, llm evals on preference datasets
Python
2
star
21

compare_github_repos

Compare github repositories by commits/w, stars, size, contributors, and other advanced statistics.
JavaScript
2
star
22

join-dic-hunspell

Join dic files to make a dic file for hunspell
Python
2
star
23

lie_elicitation_prompts

Research dataset. We use prompts to get LLM's to lie. Using sys prompts and multi shot examples
Jupyter Notebook
2
star
24

LoRA_are_lie_detectors

Experiment to see if low rank adapters can work as interventions for lie detection on LLM's
Jupyter Notebook
2
star
25

train-seismic-interp

Interpret a synthetic seismic line so you can measure and improve your error.
JavaScript
1
star
26

repr-preference-optimization

Python
1
star
27

cardsforscience

cardsforscience.com a solitaire game where you work out the secret rule (inspired by Eleusis)
JavaScript
1
star
28

iris_bigvae

experiment: IRIS but with pretrained LLM
Jupyter Notebook
1
star