Menu
Posters
Thu, Mar 31, 2022
EfficientML 2022: Two Sparsities are Better than One: Efficient Sparse-Sparse ConvNets
In this poster, we present Complementary Sparsity, a structured weight sparsity technique that provides a foundation for the efficient exploitation of Activation Sparsity and Sparse-Sparse DNNs. Lawrence Spracklen and Subutai Ahmad presented this poster at the Bay Area Efficient ML Workshop on March 31, 2022.
Wed, Sep 22, 2021
Bernstein Conference 2021: Going Beyond the Point Neuron: Active Dendrites and Sparse Representations for Continual Learning
In this poster, we suggest that incorporating the structural properties of active dendrites and sparse representations can help improve the accuracy of ANNs in a continual learning scenario.
Thu, Jul 08, 2021
SNN Workshop 2021: How Can We Be So Slow? Realizing the Performance Benefits of Sparse Networks
In this poster, we present the techniques we developed to achieve a 100x inference task speedup from sparsity and discuss how many of the learnings could be applied to develop fast sparse networks on CPUs. Numenta Director of ML Architecture Lawrence Spracklen and Software Architect Kevin Hunter presented this poster at the SNN 2021 Workshop.
Mon, Jul 05, 2021
CNS 2021: Hippocampal Spatial Mapping as Fast Graph Learning
In this poster, we show that hippocampal modules may dynamically create graphs representing spatial arrangements, and it opens up new ways of understanding how animals make rapid spatial and non-spatial inferences. Numenta Senior Researcher Marcus Lewis presented this poster at the CNS 2021 Meeting.
Marcus Lewis • Senior Researcher Sun, Jul 04, 2021
CNS 2021: Going Beyond the Point Neuron: Active Dendrites and Sparse Representations for Continual Learning
In this poster, we suggest that incorporating the structural properties of active dendrites and sparse representations can help improve the accuracy of ANNs in a continual learning scenario. Numenta Researcher Karan Grewal presented this poster at the CNS 2021 Meeting.
Fri, Feb 26, 2021
COSYNE 2021: Grid Cell Path Integration for Movement-Based Visual Object Recognition
In this poster, we explore how grid cell-based path integration in a cortical network can enable reliable recognition of visual objects given an arbitrary sequence of inputs. Numenta Visiting Scholar Niels Leadholm presented this poster at the COSYNE 2021 conference.
Stay in the loop.
Sign up for our newsletter. We respect your privacy.