Search
Now showing items 1-10 of 21
Sufficient Conditions for Uniform Stability of Regularization Algorithms
(2009-12-01)
In this paper, we study the stability and generalization properties of penalized empirical-risk minimization algorithms. We propose a set of properties of the penalty term that is sufficient to ensure uniform ?-stability: ...
Vision Review
(MIT Artificial Intelligence Laboratory, 1978-05)
Artificial Intelligence and Robotics
(1984-02-01)
Since Robotics is the field concerned with the connection of perception to action, Artificial Intelligence must have a central role in Robotics if the connection is to be intelligent. Artificial Intelligence addresses ...
Stochastic Digital Circuits for Probabilistic Inference
(2008-11-24)
We introduce combinational stochastic logic, an abstraction that generalizes deterministic digital circuit design (based on Boolean logic gates) to the probabilistic setting. We show how this logic can be combined with ...
Learning and Invariance in a Family of Hierarchical Kernels
(2010-07-30)
Understanding invariance and discrimination properties of hierarchical models is arguably the key to understanding how and why such models, of which the the mammalian visual system is one instance, can lead to good ...
Notes on the Shannon Entropy of the Neural Response
(2009-10-09)
In these notes we focus on the concept of Shannon entropy in an attempt to provide a systematic way of assessing the discrimination properties of the neural response, and quantifying the role played by the number of layers ...
CogSci to AI: It's the Brainware, Stupid!
(2006-03)
Current modularization techniques fail when applied to hard AI problems.But cognitive science shows that the mind has modules specialized for particular functions.Unlike current engineered modules, the modules of themind ...
Learning by Learning To Communicate
(2007-08-23)
Human intelligence is a product of cooperation among many different specialists. Much of this cooperation must be learned, but we do not yet have a mechanism that explains how this might happen for the "high-level" agile ...
Cognitive Security for Personal Devices
(2008-03-17)
Humans should be able to think of computers as extensions of their body, as craftsmen do with their tools. Current security models, however, are too unlike those used in human minds---for example, computers authenticate ...
Program Improvement by Automatic Redistribution of Intermediate Results
(1991-02-01)
Introducing function sharing into designs allows eliminating costly structure by adapting existing structure to perform its function. This can eliminate many inefficiencies of reusing general componentssin specific ...