Learning hierarchical categories in deep neural networks

By Andrew M. Saxe, James L. McClelland, Surya Ganguli. 2013

22 citations recorded by the source corpus.

Subfields: Representation & Self-Supervised Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Representation & Self-Supervised Learning

Citations in the corpus

Implicit Regularization of Discrete Gradient Dynamics in Deep Linear Neural Networks (2019, methodology): “Prior work [Saxe et al., 2013, 2014, Advani and Saxe, 2017, Saxe et al., 2018, Lampinen and Ganguli, 2019] studied the gradient dynamics of two-layer linear networks and proved a result similar to our Thm. 2.”
Active Long Term Memory Networks (2016, methodology): “y, we demonstrate the ability of A-LTM to preserve memory during domain adaptation with and without access to replays of the previous environment. The datasets used are: SyntheticHierarchicalFeatures[35]: we employ a procedure based on independent sampling from a branching diffusion process, previou”
On the Learning Dynamics of Deep Neural Networks (2018, methodology): “It is an analogue to the orthogonal initialization used in Saxe et al. (2013b).”
Towards multi-modal causability with Graph Neural Networks enabling information fusion for explainable AI (2021, background): “There exist some promising approaches which aim at capturing better model hierarchical relationships or causality mechanisms [68,69].”
What Learning Systems do Intelligent Agents Need? Complementary Learning Systems Theory Updated. (2016, unknown): “…of increasingly complex and abstract mappings [16] are balanced here by the strong interdependencies among connection weights in deep networks [19,20] such that the weights are learned gradually through extensive, repeated, and interleaved exposure to an ensemble of training examples that…”