30 citations · 63 across the 10 of their papers we have counts for
4 papers · 1 filter
Stochastic Prototype Embeddings
Tyler R. Scott, Karl Ridgeway, Michael C. Mozer
Supervised deep-embedding methods project inputs of a domain to a representational space in which same-class instances lie near one another and different-class instances lie far ap…
Convolutional Bipartite Attractor Networks
Michael Iuzzolino, Yoram Singer, Michael C. Mozer
In human perception and cognition, a fundamental operation that brains perform is interpretation: constructing coherent neural states from noisy, incomplete, and intrinsically ambi…
State-Reification Networks: Improving Generalization by Modeling the Distribution of Hidden Representations
Alex Lamb, Jonathan Binas, Anirudh Goyal +5
Machine learning promises methods that generalize well from finite labeled data. However, the brittleness of existing neural net approaches is revealed by notable failures, such as…
Sequential mastery of multiple visual tasks: Networks naturally learn to learn and forget to forget
Guy Davidson, Michael C. Mozer
We explore the behavior of a standard convolutional neural net in a continual-learning setting that introduces visual classification tasks sequentially and requires the net to mast…