Keith Bonawitz

Suggest Changes
Michael I. Jordan20
Dan Klein15
Brian Christopher Milch12
Matthew J. Beal11
Carl E. Rasmussen11
11Stuart J. Russell
11Vikash K. Mansinghka
10Andrew D. Gordon
10James Margetson
10Jurgen Van Gael

Filter Results:

  • Full text PDF available (8)

Publication Year

2003
2017
  • This year (1)
  • Last 5 years (3)
  • Last 10 years (6)

Publication Type

Co-author

Journals and Conferences

Key Phrases

Learn More
Church: a language for generative models
Formal languages for probabilistic modeling enable re-use, modularity, and descriptive clarity, and can foster generic inference techniques. We introduce Church, a universal language for describing stochastic generative processes. Church is based on the Lisp model of lambda calculus, containing a pure Lisp as its deterministic subset. The semantics of… (More)
Composable probabilistic inference with BLAISE
If we are to understand human-level cognition, we must understand how the mind finds the patterns that underlie the incomplete, noisy, and ambiguous data from our senses and that allow us to generalize our experiences to new situations. A wide variety of commercial applications face similar issues: industries from health services to business intelligence to… (More)
Church: a language for generative models with non-parametric memoization and approximate inference
Formal languages for probabilistic modeling enable re-use, modularity, and descriptive clarity, and can foster generic inference techniques. We introduce Church, a universal language for describing stochastic generative processes. Church is based on the Lisp model of lambda calculus, containing a pure Lisp as its deterministic subset. The semantics of… (More)
Practical Secure Aggregation for Federated Learning on User-Held Data
Secure Aggregation protocols allow a collection of mutually distrust parties, each holding a private value, to collaboratively compute the sum of those values without revealing the values themselves. We consider training a deep neural network in the Federated Learning model, using distributed stochastic gradient descent across user-held training data on… (More)
An Architecture For Word Learning Using Bidirectional Multimodal Structural Alignment
Learning of new words is assisted by contextual information. This context can come in several forms, including observations in nonlinguistic semantic domains, as well as the linguistic context in which the new word was presented. We outline a general architecture for word learning, in which structural alignment coordinates this contextual information in… (More)
Bidirectional Natural Language Parsing using Streams and Counterstreams
This thesis investigates the bidirectional exchange of information between linguistic and non-linguistic semantic inputs containing ambiguities. Such exchange is critical to Cognitively Complete Systems, in which collections of related representations and processes cooperate for their mutual problem-solving benefit. The exchange paradigm of reconciliation… (More)
  • ‹
  • 1
  • ›