Showing 1–20 of 21 results
/ Date/ Name
Sep 12, 2014Unsupervised learning of clutter-resistant visual representations from natural videosJan 7, 2018Theory of Deep Learning IIb: Optimization Properties of SGDJun 5, 2016View-tolerant face recognition and Hebbian learning imply mirror-symmetric neural tuning to head orientationApr 13, 2016Bridging the Gaps Between Residual Learning, Recurrent Neural Networks and Visual CortexDec 31, 2020Explicit regularization and implicit bias in deep network classifiers trained with the square lossMar 12, 2019Theory III: Dynamics and Generalization in Deep NetworksJul 25, 2018A Surprising Linear Relationship Predicts Test Performance in Deep NetworksMar 28, 2017Theory II: Landscape of the Empirical Risk in Deep LearningDec 28, 2024Self-Assembly of a Biologically Plausible Learning CircuitOct 17, 2015How Important is Weight Symmetry in Backpropagation?Sep 30, 2025Hierarchical Reasoning Models: Perspectives and MisconceptionsAug 25, 2019Theoretical Issues in Deep Networks: Approximation, Optimization and GeneralizationOct 19, 2016Streaming Normalization: Towards Simpler and More Biologically-plausible Normalizations for Online and Recurrent LearningNov 2, 2016Why and When Can Deep -- but Not Shallow -- Networks Avoid the Curse of Dimensionality: a ReviewMar 3, 2016Learning Functions: When Is Deep Better Than ShallowDec 30, 2017Theory of Deep Learning III: explaining the non-overfitting puzzleNov 8, 2018Biologically-plausible learning algorithms can scale to large datasetsJun 24, 2020Hierarchically Compositional Tasks and Deep Convolutional NetworksJan 18, 2017Compression of Deep Neural Networks for Image Instance RetrievalJun 29, 2018Theory IIIb: Generalization in Deep Networks