deepLearning   12653

« earlier    

[1810.04714] Training Generative Adversarial Networks with Binary Neurons by End-to-end Backpropagation
We propose the BinaryGAN, a novel generative adversarial network (GAN) that uses binary neurons at the output layer of the generator. We employ the sigmoid-adjusted straight-through estimators to estimate the gradients for the binary neurons and train the whole network by end-to-end backpropogation. The proposed model is able to directly generate binary-valued predictions at test time. We implement such a model to generate binarized MNIST digits and experimentally compare the performance for different types of binary neurons, GAN objectives and network architectures. Although the results are still preliminary, we show that it is possible to train a GAN that has binary neurons and that the use of gradient estimators can be a promising direction for modeling discrete distributions with GANs. For reproducibility, the source code is available at this https URL .
DeepLearning 
13 hours ago by researchknowledge
Twitter
데이터 학습 모델에 적합한 평가 기준은 무엇인지 간단한 예제와 레고로 친절하게 설명한 글입니다.💻

DeepLearning  from twitter_favs
yesterday by javason
Deep Learning For Coders—36 hours of lessons for free
Welcome to the start of your fast.ai journey! In today’s lesson you’ll set up your deep learning server, and train your first image classification model (a convolutional neural network, or CNN), which will learn to distinguish dogs from cats nearly perfectly. If you need help at any time, head over to forums.fast.ai where over a thousand students are discussing the course and have provided lots of tips and tricks for you.

Each lesson page includes a link to a forum topic that includes a hyperlinked timeline, links to further resources, and a discussion of the lesson. Nearly all the participants in the original in-person course said that they found these resources very important for successfully completing the course. So be sure to make the most of them! And be sure to carefully read the Getting Started page to find out how this course is designed and how to get the most out of it.
deeplearning  tutorial  course 
yesterday by rybesh
Opinion | No, A.I. Won’t Solve the Fake News Problem - The New York Times
Existing A.I. systems that have been built to comprehend news accounts are extremely limited. Such a system might be able to look at the passage from the WND article and answer a question whose answer is given directly and explicitly in the story (e.g., “Does the Boy Scouts organization accept people who identify as gay and lesbian?”). But such systems rarely go much further, lacking a robust mechanism for drawing inferences or a way of connecting to a body of broader knowledge. As Eduardo Ariño de la Rubia, a data scientist at Facebook, told us, for now “A.I. cannot fundamentally tell what’s true or false — this is a skill much better suited to humans.”

To get to where Mr. Zuckerberg wants to go will require the development of a fundamentally new A.I. paradigm, one in which the goal is not to detect statistical trends but to uncover ideas and the relations between them. Only then will such promises about A.I. become reality, rather than science fiction.
ai  news  media  journalism  facebook  tech  technology  machinelearning  deeplearning 
yesterday by msszczep
Twitter
classifiers using have surpassed human level accuracy. It uses Object Detection with Localizat…
DeepLearning  Image  from twitter
2 days ago by jhill5
[1810.01993] Exascale Deep Learning for Climate Analytics
We extract pixel-level masks of extreme weather patterns using variants of Tiramisu and DeepLabv3+ neural networks. We describe improvements to the software frameworks, input pipeline, and the network training algorithms necessary to efficiently scale deep learning on the Piz Daint and Summit systems. The Tiramisu network scales to 5300 P100 GPUs with a sustained throughput of 21.0 PF/s and parallel efficiency of 79.0%. DeepLabv3+ scales up to 27360 V100 GPUs with a sustained throughput of 325.8 PF/s and a parallel efficiency of 90.7% in single precision. By taking advantage of the FP16 Tensor Cores, a half-precision version of the DeepLabv3+ network achieves a peak and sustained throughput of 1.13 EF/s and 999.0 PF/s respectively.
machinelearning  DeepLearning 
3 days ago by researchknowledge

« earlier    

related tags

adventures  agile  ai  ann  art  article  artificialintelligence  audio  badscience  bayesian  cnn  color  computationalmusic  computers  computervision  course  courses  crypto  cuda  dance  datascience  dataset  deeplearning  deeptext  devops  docker  dropbox  embeddings  entityextraction  face  facebook  fashion  fortalk  framework  gan  government  gpu  graphicalmodel  health  hpc  ilya  image  images  javascript  journalism  language  lumos  machinelearning  manga  marketplace  mathematics  maths  media  medicine  ml  monads  music  networks  neural  neuralnetwork  neuralnetworks  neuroscience  news  nlp  ocr  online  openai  painting  paper  papers  people  photo  photography  productmanagement  programming  python  pytorch  r.deeplearning  r.machinelearning  r  rdf  recognition  recommendations  reinforcementlearning  research  resnet  scaling  science  siggraph18  simulation  sound  speech  sutskever  tech  technology  tensorflow  todo  tool  tools  transferlearning  translate  translation  translator  tutorial  video  videos  vision  voice  word2vec  wordembedding  workflow 

Copy this bookmark:



description:


tags: