From the 1 of 1.6k papers with an AI index.
24.4k citations
- University of California, BerkeleyUS95 papers
- Stanford UniversityUS79 papers
- Massachusetts Institute of TechnologyUS71 papers
- Google DeepMind (United Kingdom)GB56 papers
- Carnegie Mellon UniversityUS53 papers
- University of TorontoCA50 papers
- Princeton UniversityUS47 papers
- Cornell UniversityUS43 papers
- Columbia UniversityUS35 papers
- University of Illinois Urbana-ChampaignUS35 papers
- University of California, Santa BarbaraUS31 papers
- University of WashingtonUS30 papers
4 papers · 2 filters
Capacity and Trainability in Recurrent Neural Networks
Jasmine Collins, Jascha Sohl-Dickstein, David Sussillo
Two potential bottlenecks on the expressiveness of recurrent neural networks (RNNs) are their ability to store information about the task in their parameters, and to store informat…
Stochastic Gradient MCMC with Stale Gradients
Changyou Chen, Nan Ding, Chunyuan Li +2
Stochastic gradient MCMC (SG-MCMC) has played an important role in large-scale Bayesian learning, with well-developed theoretical convergence properties. In such applications of SG…
Semi-supervised Knowledge Transfer for Deep Learning from Private Training Data
Nicolas Papernot, Martín Abadi, Úlfar Erlingsson +2
Some machine learning applications involve training data that is sensitive, such as the medical histories of patients in a clinical trial. A model may inadvertently and implicitly…
Latent Sequence Decompositions
William Chan, Yu Zhang, Quoc Le +1
We present the Latent Sequence Decompositions (LSD) framework. LSD decomposes sequences with variable lengthed output units as a function of both the input sequence and the output…