サクサク読めて、アプリ限定の機能も多数!
トップへ戻る
やる気の出し方
cs.stanford.edu
Deep Visual-Semantic Alignments for Generating Image Descriptions We present a model that generates natural language descriptions of images and their regions. Our approach leverages datasets of images and their sentence descriptions to learn about the inter-modal correspondences between language and visual data. Our alignment model is based on a novel combination of Convolutional Neural Networks o
I have moved to ETH Zurich as an Assistant Professor. My new homepage is here.
ConvNetJS CIFAR-10 demo Description This demo trains a Convolutional Neural Network on the CIFAR-10 dataset in your browser, with nothing but Javascript. The state of the art on this dataset is about 90% accuracy and human performance is at about 94% (not perfect as the dataset can be a bit ambiguous). I used this python script to parse the original files (python version) into batches of images th
ConvNetJS Trainer demo on MNIST Description This demo lets you evaluate multiple trainers against each other on MNIST. By default I've set up a little benchmark that puts SGD/SGD with momentum/Adagrad/Adadelta/Nesterov against each other. For reference math and explanations on these refer to Matthew Zeiler's Adadelta paper (Windowgrad is Idea #1 in the paper). In my own experience, Adagrad/Adadelt
ConvNetJS Deep Q Learning Demo Description This demo follows the description of the Deep Q Learning algorithm described in Playing Atari with Deep Reinforcement Learning, a paper from NIPS 2013 Deep Learning Workshop from DeepMind. The paper is a nice demo of a fairly standard (model-free) Reinforcement Learning algorithm (Q Learning) learning to play Atari games. In this demo, instead of Atari ga
Description The library allows you to formulate and solve Neural Networks in Javascript, and was originally written by @karpathy (I am a PhD student at Stanford). However, the library has since been extended by contributions from the community and more are warmly welcome. Current support includes: Common Neural Network modules (fully connected layers, non-linearities) Classification (SVM/Softmax)
cs.stanford.edu/~quocle
ConvnetJS demo: toy 2d classification with 2-layer neural network The simulation below shows a toy binary problem with a few data points of class 0 (red) and 1 (green). The network is set up as: Feel free to change this, the text area above gets eval()'d when you hit the button and the network gets reloaded. Every 10th of a second, all points are fed to the network multiple times through the train
ConvNetJS MNIST demo Description This demo trains a Convolutional Neural Network on the MNIST digits dataset in your browser, with nothing but Javascript. The dataset is fairly easy and one should expect to get somewhere around 99% accuracy within few minutes. I used this python script to parse the original files into batches of images that can be easily loaded into page DOM with img tags. This ne
Below every paper are TOP 100 most-occuring words in that paper and their color is based on LDA topic model with k = 7. (It looks like 0 = reinforcement learning, 1 = deep learning, 2 = structured learning?, 3 = optimization?, 4 = graphical models, 5 = theory, 6 = neuroscience)
NIPS 2012 papers (in nicer format than this) maintained by @karpathy source code on github Below every paper are TOP 100 most-occuring words in that paper and their color is based on LDA topic model with k = 7. (It looks like 0 = theory, 1 = reinforcement learning, 2 = graphical models, 3 = deep learning/vision, 4 = optimization, 5 = neuroscience, 6 = embeddings etc.)
cs.stanford.edu/~karpathy
Supervised Random Walks: Predicting and Recommending Links in Social Networks Lars Backstrom Facebook lars@facebook.com Jure Leskovec Stanford University jure@cs.stanford.edu ABSTRACT Predicting the occurrence of links is a fundamental problem in net- works. In the link prediction problem we are given a snapshot of a network and would like to infer which interactions among existing members are lik
I am Professor of Computer Science at Stanford University. My general research area is applied machine learning for large interconnected systems focusing on modeling complex, richly-labeled relational structures, graphs, and networks for systems at all scales, from interactions of proteins in a cell to interactions between humans in a society. Applications include commonsense reasoning, recommende
Firefox 3 lets you tag your bookmarks, but it doesn't give you a great way to browse your bookmarks by their tags. TagSifter tries to. Click a bunch of tags in the sidebar or menu to see the bookmarks and other tags that are related. Use the related tags to quickly filter your search. Or, if you can handle real ultimate power, use a full range of set operators in arbitrary expressions to s
このページを最初にブックマークしてみませんか?
『Computer Science』の新着エントリーを見る
j次のブックマーク
k前のブックマーク
lあとで読む
eコメント一覧を開く
oページを開く