• Publications
  • Influence
Learning the parts of objects by non-negative matrix factorization
TLDR
An algorithm for non-negative matrix factorization is demonstrated that is able to learn parts of faces and semantic features of text and is in contrast to other methods that learn holistic, not parts-based, representations.
Algorithms for Non-negative Matrix Factorization
TLDR
Two different multiplicative algorithms for non-negative matrix factorization are analyzed and one algorithm can be shown to minimize the conventional least squares error while the other minimizes the generalized Kullback-Leibler divergence.
Query by committee
TLDR
It is suggested that asymptotically finite information gain may be an important characteristic of good query algorithms, in which a committee of students is trained on the same data set.
Connectomic reconstruction of the inner plexiform layer in the mouse retina
TLDR
Circuit motifs that emerge from the data indicate a functional mechanism for a known cellular response in a ganglion cell that detects localized motion, and predict that another ganglions cell is motion sensitive.
Selective Sampling Using the Query by Committee Algorithm
TLDR
It is shown that if the two-member committee algorithm achieves information gain with positive lower bound, then the prediction error decreases exponentially with the number of queries, and this exponential decrease holds for query learning of perceptrons.
Simple models for reading neuronal population codes.
TLDR
It is found that for threshold linear networks the transfer of perceptual learning is nonmonotonic, and although performance deteriorates away from the training stimulus, it peaks again at an intermediate angle.
Trainable Weka Segmentation: a machine learning tool for microscopy pixel classification
TLDR
The Trainable Weka Segmentation (TWS), a machine learning tool that leverages a limited number of manual annotations in order to train a classifier and segment the remaining data automatically, is introduced.
How the brain keeps the eyes still.
  • H. Seung
  • Psychology
    Proceedings of the National Academy of Sciences…
  • 12 November 1996
TLDR
Existing experimental data are reinterpreted as evidence for an "attractor hypothesis" that the persistent patterns of activity observed in this network form an attractive line of fixed points in its state space.
Digital selection and analogue amplification coexist in a cortex-inspired silicon circuit
TLDR
The model of cortical processing is presented as an electronic circuit that emulates this hybrid operation, and so is able to perform computations that are similar to stimulus selection, gain modulation and spatiotemporal pattern generation in the neocortex.
...
...