DSpace at MIT
(28,967 recursos)
This site is a university repository providing access to the publication output of the institution. Registered users can set up email alerts to notify them of newly added relevant content. A certain level of encryption and security is embedded in the site which may cause some users accessibility problems.
Mostrando recursos 21 - 40 de 123
21.
Model Selection in Summary Evaluation - Perez-Breva, Luis; Yoshimi, Osamu
A difficulty in the design of automated text summarization algorithms is in the objective evaluation.
23.
Model-Based Matching by Linear Combinations of Prototypes - Jones, Michael J.; Poggio, Tomaso
We describe a method for modeling object classes (such as faces) using 2D example images and an algorithm for matching a model to a novel image.
24.
Learning Linear, Sparse, Factorial Codes - Olshausen, Bruno A.
In previous work (Olshausen & Field 1996), an algorithm was described for learning linear sparse codes which, when trained on natural images, produces a set of basis functions that are spatially localized, oriented, and bandpass (i.e., wavelet-like).
25.
Probabilistic Independence Networks for Hidden Markov Probability Models - Smyth, Padhraic; Heckerman, David; Jordan, Michael
Graphical techniques for modeling the dependencies of randomvariables have been explored in a variety of different areas includingstatistics, statistical physics, artificial intelligence, speech recognition, image processing, and genetics.Formalisms for manipulating these models have been developedrelatively independently in these research communities.
26.
Neural Networks - Jordan, Michael I.; Bishop, Christopher M.
We present an overview of current research on artificial neural networks, emphasizing a statistical perspective.
28.
Factorial Hidden Markov Models - Ghahramani, Zoubin; Jordan, Michael I.
Within this framework, we derive a learning algorithm based on the Expectation--Maximization (EM) procedure for maximum likelihood estimation.
29.
Fast Learning by Bounding Likelihoods in Sigmoid Type Belief Networks - Jaakkola, Tommi S.; Saul, Lawrence K.; Jordan, Michael I.
Sigmoid type belief networks, a class of probabilistic neural networks, provide a natural framework for compactly representing probabilistic information in a variety of unsupervised and supervised learning problems.
32.
Active Learning with Statistical Models - Cohn, David A.; Ghahramani, Zoubin; Jordan, Michael I.
We review how these techniques have been used with feedforward neural networks.
34.
View-Based Strategies for 3D Object Recognition - Sinha, Pawan; Poggio, Tomaso
A persistent issue of debate in the area of 3D object recognition concerns the nature of the experientially acquired object models in the primate visual system.
36.
The Logical Problem of Language Change - Niyogi, Partha; Berwick, Robert
While the language learning problem has focused on the behavior of individuals and how they acquire a particular grammar from a class of grammars ${cal G}$, here we consider a population of such learners and investigate the emergent, global population characteristics of linguistic communities over several generations.
37.
Verb Classes and Alternations in Bangla, German, English, and Korean - Jones, Douglas A.; Berwick, Robert C.; Cho, Franklin; Khan, Zeeshan; Kohl, Karen T.; Nomura, Naoyuki; Radhakrishnan, Anand; Sauerland, Ulrich; Ulicny, Brian
Our work is based on the English Verb Classes and Alternations of (Levin, 1993).
38.
A Dynamical Systems Model for Language Change - Niyogi, Partha; Berwick, Robert
We apply the computer model to the historical loss of Verb Second from Old French to modern French, showing that otherwise adequate grammatical theories can fail our new evolutionary criterion.
40.
Sequential Optimal Recovery: A Paradigm for Active Learning - Niyogi, Partha
We demonstrate the application of this general formulation to two special cases of functions on the real line 1) monotonically increasing functions and 2) functions with bounded derivative.
21.
