Search Results for author:
Found 13 papers, 8 papers with code
[Call for Papers] The 2nd BabyLM Challenge: Sample-efficient pretraining on a developmentally plausible corpus
The big changes for this year's competition are as follows: First, we replace the loose track with a paper track, which allows (for example) non-model-based submissions, novel cognitively-inspired benchmarks, or analysis techniques.
Lexicon-Level Contrastive Visual-Grounding Improves Language Modeling
Today's most accurate language models are trained on orders of magnitude more language data than human language learners receive - but with no supervision from other sensory modalities that play a crucial role in human learning.
Visual Grounding Helps Learn Word Meanings in Low-Data Regimes
But to achieve these results, LMs must be trained in distinctly un-human-like ways - requiring orders of magnitude more language data than children receive during development, and without perceptual or social context.
Call for Papers -- The BabyLM Challenge: Sample-efficient pretraining on a developmentally plausible corpus
In partnership with CoNLL and CMCL, we provide a platform for approaches to pretraining with a limited-size corpus sourced from data inspired by the input to children.
How Well Do Unsupervised Learning Algorithms Model Human Real-time and Life-long Learning?
Taken together, our benchmarks establish a quantitative way to directly compare learning between neural networks models and human learners, show how choices in the mechanism by which such algorithms handle sample comparison and memory strongly impact their ability to match human learning abilities, and expose an open problem space for identifying more flexible and robust visual self-supervision algorithms.
Conditional Negative Sampling for Contrastive Learning of Visual Representations
To do this, we introduce a family of mutual information estimators that sample negatives conditionally -- in a "ring" around each positive.
On Mutual Information in Contrastive Learning for Visual Representations
Reformulating previous learning objectives in terms of mutual information also simplifies and stabilizes them.
Local Label Propagation for Large-Scale Semi-Supervised Learning
It then propagates pseudolabels from known to unknown datapoints in a manner that depends on the local geometry of the embedding, taking into account both inter-point distance and local data density as a weighting on propagation likelihood.
Unsupervised Learning from Video with Deep Neural Embeddings
Because of the rich dynamical structure of videos and their ubiquity in everyday life, it is a natural idea that video data could serve as a powerful unsupervised learning signal for training visual representations in deep neural networks.
Local Aggregation for Unsupervised Learning of Visual Embeddings
Unsupervised approaches to learning in neural networks are of substantial interest for furthering artificial intelligence, both because they would enable the training of networks without the need for large numbers of expensive annotations, and because they would be better models of the kind of general-purpose learning deployed by humans.
Ranked #12 on
Contrastive Learning
on imagenet-1k
Flexible Neural Representation for Physics Prediction
Humans have a remarkable capacity to understand the physical dynamics of objects in their environment, flexibly capturing complex structures and interactions at multiple levels of detail.
Toward Goal-Driven Neural Network Models for the Rodent Whisker-Trigeminal System
In large part, rodents see the world through their whiskers, a powerful tactile sense enabled by a series of brain areas that form the whisker-trigeminal system.
Predictive Encoding of Contextual Relationships for Perceptual Inference, Interpolation and Prediction
We propose a new neurally-inspired model that can learn to encode the global relationship context of visual events across time and space and to use the contextual information to modulate the analysis by synthesis process in a predictive coding framework.
