Browsing Faculty of Arts and Sciences by Author "Cox, David"
Now showing items 1-10 of 10
-
Deep Predictive Coding Networks for Video Prediction and Unsupervised Learning
Lotter, William Edward; Kreiman, Gabriel; Cox, David Daniel (2016)While great strides have been made in using deep learning algorithms to solve supervised learning tasks, the problem of unsupervised learning - leveraging unlabeled examples to learn about the structure of a domain - remains ... -
A High-Throughput Screening Approach to Discovering Good Forms of Biologically Inspired Visual Representation
Pinto, Nicolas; Doukhan, David; DiCarlo, James J.; Cox, David Daniel (Public Library of Science, 2009)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 ... -
Hyperparameter Optimization and Boosting for Classifying Facial Expressions: How good can a “Null” Model be?
Bergstra, James; Cox, David Daniel (ICML, 2013)One of the goals of the ICML workshop on representation and learning is to establish benchmark scores for a new data set of labeled facial expressions. This paper presents the performance of a "Null" model consisting of ... -
Input-aware auto-tuning of compute-bound HPC kernels
Tillet, Philippe; Cox, David (ACM, 2017-11-12)Efficient implementations of HPC applications for parallel architectures generally rely on external software packages (e.g., BLAS, LAPACK, CUDNN). While these libraries provide highly optimized routines for certain ... -
Making a Science of Model Search: Hyperparameter Optimization in Hundreds of Dimensions for Vision Architectures
Bergstra, J.; Yamins, D.; Cox, David Daniel (JMLR, 2013)Many computer vision algorithms depend on configuration settings that are typically hand-tuned in the course of evaluating the algorithm for a particular data set. While such parameter tuning is often presented as being ... -
A Micro-CT-Based Method for Quantitative Brain Lesion Characterization and Electrode Localization
Masís, Javier; Mankus, David; Wolff, Steffen; Guitchounts, Grigori; Cox, DavidLesion verification and quantification is traditionally done via histological examination of sectioned brains, a time-consuming process that relies heavily on manual estimation. Such methods are particularly problematic ... -
A neural network trained for prediction mimics diverse features of biological neurons and perception
Lotter, William; Kreiman, Gabriel; Cox, David (Springer Science and Business Media LLC, 2020-04-20) -
Perceptual Annotation: Measuring Human Vision to Improve Computer Vision
Scheirer, Walter Jerome; Anthony, Samuel English; Nakayama, Ken; Cox, David Daniel (Institute of Electrical & Electronics Engineers (IEEE), 2014)For many problems in computer vision, human learners are considerably better than machines. Humans possess highly accurate internal recognition and learning mechanisms that are not yet understood, and they frequently have ... -
Rats maintain a binocular field centered on the horizon
Meister, Markus; Cox, David (F1000Research, 2013)In this letter, we attempt to correct a potentially serious misperception arising from the paper “Rats maintain an overhead binocular field at the expense of constant fusion”. While the authors repeatedly emphasize that ... -
Why is Real-World Visual Object Recognition Hard?
Pinto, Nicolas; Cox, David Daniel; DiCarlo, James J (Public Library of Science, 2008)Progress in understanding the brain mechanisms underlying vision requires the construction of computational models that not only emulate the brain's anatomy and physiology, but ultimately match its performance on visual ...