A High-Throughput Screening Approach to Discovering Good Forms of Biologically Inspired Visual Representation
Name
Pinto-2009-A High-Throughput Sc.pdf
Size
549.72 KB
Format
Adobe PDF
Checksum (MD5)
d05890b66fb330aa7d9a92351e59bad4
Author(s)
Cox, David D.
Pinto, Nicolas
Doukhan, David
DiCarlo, James
Date Issued
November 2009
Journal
PLoS Computational Biology
Publisher
Public Library of Science
Citation
Pinto, Nicolas et al. “A High-Throughput Screening Approach to Discovering Good Forms of Biologically Inspired Visual Representation.” PLoS Comput Biol 5.11 (2009): e1000579. © 2009 Pinto et al.
Version
Final published version
Abstract
While many models of biological object recognition share a common set of ‘‘broad-stroke’’ properties, the performance of
any one model depends strongly on the choice of parameters in a particular instantiation of that model—e.g., the number
of units per layer, the size of pooling kernels, exponents in normalization operations, etc. Since the number of such
parameters (explicit or implicit) is typically large and the computational cost of evaluating one particular parameter set is
high, the space of possible model instantiations goes largely unexplored. Thus, when a model fails to approach the abilities
of biological visual systems, we are left uncertain whether this failure is because we are missing a fundamental idea or
because the correct ‘‘parts’’ have not been tuned correctly, assembled at sufficient scale, or provided with enough training.
Here, we present a high-throughput approach to the exploration of such parameter sets, leveraging recent advances in
stream processing hardware (high-end NVIDIA graphic cards and the PlayStation 3’s IBM Cell Processor). In analogy to highthroughput
screening approaches in molecular biology and genetics, we explored thousands of potential network
architectures and parameter instantiations, screening those that show promising object recognition performance for further
analysis. We show that this approach can yield significant, reproducible gains in performance across an array of basic object
recognition tasks, consistently outperforming a variety of state-of-the-art purpose-built vision systems from the literature.
As the scale of available computational power continues to expand, we argue that this approach has the potential to greatly
accelerate progress in both artificial vision and our understanding of the computational underpinning of biological vision.
MIT Department
Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences
McGovern Institute for Brain Research at MIT
Terms of Use
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Persistent DSpace Link
DOI of Published Version
http://dx.doi.org/10.1371/journal.pcbi.1000579
