deep-learning   7950

« earlier    

Meta-Learning: Learning to Learn Fast
Meta-learning, also known as “learning to learn”, intends to design models that can learn new skills or adapt to new environments rapidly with a few training examples. There are three common approaches: 1) learn an efficient distance metric (metric-based); 2) use (recurrent) network with external or internal memory (model-based); 3) optimize the model parameters explicitly for fast learning (optimization-based).
machine-learning  deep-learning 
yesterday by doneata
Colorizing and Restoring Old Images with Deep Learning
Jason Antic's DeOldify deep learning project not only colorizes images but also restores them with stunning results. Learn how in this FloydHub interview.
machinelearning  python  deep-learning  tutorial 
yesterday by cychong47
Open AI – Spinning Up
Welcome to Spinning Up in Deep RL! This is an educational resource produced by OpenAI that makes it easier to learn about deep reinforcement learning (deep RL).

For the unfamiliar: reinforcement learning (RL) is a machine learning approach for teaching agents how to solve tasks by trial and error. Deep RL refers to the combination of RL with deep learning.

This module contains a variety of helpful resources, including:

a short introduction to RL terminology, kinds of algorithms, and basic theory, an essay about how to grow into an RL research role, a curated list of important papers organized by topic, a well-documented code repo of short, standalone implementations of key algorithms, and a few exercises to serve as warm-ups.
reinforcement-learning  deep-learning  tutorial 
3 days ago by doneata

« earlier    

related tags

(it-ain't)  2018  ai  aicreated  algorithms  alternative  andrew  artificial-intelligence  arxiv  aws  backprop  backpropagation  bayesian  best-results  binder  blog  book  build  builder  causal-inference  causality  cfr  cheatsheet  chess  cifar  classical  code-completion  code  compiler  conversion  cosine-distance  counterfactual  course  data-science  data-viz  dataset  datasets  deeplearning  deepmind  deployment  development  differential-equations  discrete-and-continuous-sittin-in-a-tree  disguise  dl  docker  download  elastic  embedding  embeddings  evolution  example  face  facebook  faces  fair  feature-construction  federation  finance  flux  forecasting  framework  free  funnel  game-theory  games  gan  gans  gbm  generative-adversarial-network  genetic-programming  github-star  github  golang  google  gpu  ground-truth  groundtruth  horizon  howto  ifttt  image-generation  image-processing  image-recognition  imagenet  images  inference  jit  journalism  julia  jupyter-notebook  jupyter  jupyterhub  kaggle  keras  labeling  lang:python  learning  lecture  lstm  machine-learning  machine_learning  machinelearning  marketing-funnel  marketing  math  me  media  ml  mltheory  mnist  model  music  neat  neo  neural-network  neural-networks  neuralnetwork  neuralnetworks  neuroevolution  nips-2018  nips  nlp  node.js  object-recognition  odenets  open-ai  optimization  optimsation  paper  pdf  practical  prediction  privacy  proceedings  production  programming  pycoders325  python  pytorch  ranking  regret-minimiation  reinforcement-learning  remote  representation  richard  rl  rnn  robots  sagemaker  script  security  seq2seq  server  similarity  software  standford  star-craft  starcraft  statistics  streamlit  study-group  style-transfer  t-sne  tencent  tensor-flow  time-series  to-write-about  todo:interarma  trace  trading  turing-test  tutorial  type:framework  video  visualization  word-embedding  word2vec  xai  youtube 

Copy this bookmark: