romaingratier Goto Github PK

black-box_optimization_via_deep_generative-exploratory_networks

Deep neural networks have garnered tremendous excitement in recent years thanks to their superior learning capacity in the presence of abundant data resources. However, collecting an exhaustive dataset covering all possible scenarios is often slow, expensive, and even impractical. The goal of this project is to devise a new learning framework that can learn from a finite dataset and noisy feedback of data properties to discover novel samples of particular interest. We will design and implement algorithms to interweave emerging deep generative modeling with classical Markov decision processes. We will evaluate our method in comparison to existing approaches through extensive experiments, including but not limited to visual semantic extrapolation and natural adversarial examples in the context of autonomous vehicles.

datascience

Curated list of Python resources for data science.

deepfrench

NLP French language model implementing ULMFiT

gan_inpainting_for_pose_estimation

tackle pose estimation while occlusion appear with generative adversarial models

gandissect

Pytorch-based tools for visualizing and understanding the neurons of a GAN. https://gandissect.csail.mit.edu/

generative_inpainting

DeepFill v1/v2 with Contextual Attention and Gated Convolution, CVPR 2018, and ICCV 2019 Oral

image-recognition-groceries

Test machine learning power to classify product

implicit

Fast Python Collaborative Filtering for Implicit Feedback Datasets

recipe-app-api

recipes-telegram-bot

Generate and recommend recipes based on photos of your fridge

telegram-coffee-break

It's time to take a coffee break! your python code is running, and you'll be notified through telegram to see the progress of your code.

test-hierarchy-interactive

Created with CodeSandbox

vue.js-tree-data-builder

Build data trees optimized for d3 structure quickly with this app!