Dimensionality Reduction by Learning an Invariant Mapping
International audience
Publications
6 shownDeep neural network improves fracture detection by clinicians
Significance Historically, computer-assisted detection (CAD) in radiology has failed to achieve improvements in diagnostic accuracy, decreasing clinician sensitivity and leading...
Learning a Similarity Metric Discriminatively, with Application to Face Verification
International audience
Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks
One long-term goal of machine learning research is to produce methods that are applicable to reasoning and natural language, in particular building an intelligent dialogue agent...
Efficient Learning of Sparse Representations with an Energy-Based Model
We describe a novel unsupervised method for learning sparse, overcomplete features. The model uses a linear encoder, and a linear decoder preceded by a sparsifying non-linearity...
The Goldilocks Principle: Reading Children's Books with Explicit Memory Representations
Abstract: We introduce a new test of how well language models capture meaning in children's books. Unlike standard language modelling benchmarks, it distinguishes the task of pr...
Frequent Co-Authors
Researcher Info
- h-index
- 6
- Publications
- 6
- Citations
- 11,550
- Institution
- New York University
External Links
Identifiers
- ORCID
- 0009-0009-6637-2230
Impact Metrics
h-index
6
h-index: Number of publications with at least h citations each.