Share This Author
A global geometric framework for nonlinear dimensionality reduction.
An approach to solving dimensionality reduction problems that uses easily measured local metric information to learn the underlying global geometry of a data set and efficiently computes a globally optimal solution, and is guaranteed to converge asymptotically to the true structure.
Human-level concept learning through probabilistic program induction
A computational model is described that learns in a similar fashion and does so better than current deep learning algorithms and can generate new letters of the alphabet that look “right” as judged by Turing-like tests of the model's output in comparison to what real humans produce.
Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling
- Jiajun Wu, Chengkai Zhang, Tianfan Xue, Bill Freeman, J. Tenenbaum
- Computer ScienceNIPS
- 24 October 2016
A novel framework, namely 3D Generative Adversarial Network (3D-GAN), which generates 3D objects from a probabilistic space by leveraging recent advances in volumetric convolutional networks and generative adversarial nets, and a powerful 3D shape descriptor which has wide applications in 3D object recognition.
Meta-Learning for Semi-Supervised Few-Shot Classification
- Mengye Ren, Eleni Triantafillou, R. Zemel
- Computer ScienceInternational Conference on Learning…
- 15 February 2018
This work proposes novel extensions of Prototypical Networks that are augmented with the ability to use unlabeled examples when producing prototypes, and confirms that these models can learn to improve their predictions due to unlabeling examples, much like a semi-supervised algorithm would.
The Large-Scale Structure of Semantic Networks: Statistical Analyses and a Model of Semantic Growth
A simple model for semantic growth is described, in which each new word or concept is connected to an existing network by differentiating the connectivity pattern of an existing node, which generates appropriate small-world statistics and power-law connectivity distributions.
Topics in semantic representation.
This article analyzes the abstract computational problem underlying the extraction and use of gist, formulating this problem as a rational statistical inference that leads to a novel approach to semantic representation in which word meanings are represented in terms of a set of probabilistic topics.
Learning Systems of Concepts with an Infinite Relational Model
- Charles Kemp, J. Tenenbaum, T. Griffiths, Takeshi Yamada, N. Ueda
- Computer ScienceAAAI Conference on Artificial Intelligence
- 16 July 2006
A nonparametric Bayesian model is presented that discovers systems of related concepts and applies the approach to four problems: clustering objects and features, learning ontologies, discovering kinship systems, and discovering structure in political data.
Hierarchical Topic Models and the Nested Chinese Restaurant Process
A Bayesian approach is taken to generate an appropriate prior via a distribution on partitions that allows arbitrarily large branching factors and readily accommodates growing data collections.
One shot learning of simple visual concepts
- B. Lake, R. Salakhutdinov, Jason Gross, J. Tenenbaum
- Computer ScienceAnnual Meeting of the Cognitive Science Society
A generative model of how characters are composed from strokes is introduced, where knowledge from previous characters helps to infer the latent strokes in novel characters, using a massive new dataset of handwritten characters.
Separating Style and Content with Bilinear Models
A general framework for learning to solve two-factor tasks using bilinear models, which provide sufficiently expressive representations of factor interactions but can nonetheless be fit to data using efficient algorithms based on the singular value decomposition and expectation-maximization are presented.