1 code implementation • 31 Dec 2021 • Abhiram Iyer, Karan Grewal, Akash Velu, Lucas Oliveira Souza, Jeremy Forest, Subutai Ahmad
Next, we study the performance of this architecture on two separate benchmarks requiring task-based adaptation: Meta-World, a multi-task reinforcement learning environment where a robotic agent must learn to solve a variety of manipulation tasks simultaneously; and a continual learning benchmark in which the model's prediction task changes throughout training.
no code implementations • 27 Dec 2021 • Kevin Lee Hunter, Lawrence Spracklen, Subutai Ahmad
In this article we introduce Complementary Sparsity, a novel technique that significantly improves the performance of dual sparse networks on existing hardware.
1 code implementation • 17 Feb 2021 • Niels Leadholm, Marcus Lewis, Subutai Ahmad
Grid cells enable the brain to model the physical space of the world and navigate effectively via path integration, updating self-position using information from self-movement.
1 code implementation • 2 Dec 2019 • Jeremy Gordon, David Rawlinson, Subutai Ahmad
In sequence learning tasks such as language modelling, Recurrent Neural Networks must learn relationships between input features separated by time.
3 code implementations • 27 Mar 2019 • Subutai Ahmad, Luiz Scheinkman
Most artificial networks today rely on dense representations, whereas biological networks rely on sparse representations.
4 code implementations • 8 Jul 2016 • Subutai Ahmad, Scott Purdy
Much of the worlds data is streaming, time-series data, where anomalies give significant information in critical situations.
Ranked #8 on Anomaly Detection on Numenta Anomaly Benchmark
no code implementations • 5 Jan 2016 • Subutai Ahmad, Jeff Hawkins
Our model is inspired by recent experimental findings on active dendritic processing and NMDA spikes in pyramidal neurons.
1 code implementation • 17 Dec 2015 • Yuwei Cui, Subutai Ahmad, Jeff Hawkins
In this paper, we analyze properties of HTM sequence memory and apply it to sequence learning and prediction problems with streaming data.
1 code implementation • 31 Oct 2015 • Jeff Hawkins, Subutai Ahmad
Given the similarity of excitatory neurons throughout the neocortex and the importance of sequence memory in inference and behavior, we propose that this form of sequence memory is a universal property of neocortical tissue.
3 code implementations • 12 Oct 2015 • Alexander Lavin, Subutai Ahmad
Here we propose the Numenta Anomaly Benchmark (NAB), which attempts to provide a controlled and repeatable environment of open-source tools to test and measure anomaly detection algorithms on streaming data.
Ranked #4 on Anomaly Detection on Numenta Anomaly Benchmark
no code implementations • 8 May 2015 • Sebastian Billaudelle, Subutai Ahmad
Hierarchical Temporal Memory (HTM) is a computational theory of machine intelligence based on a detailed study of the neocortex.
no code implementations • 25 Mar 2015 • Subutai Ahmad, Jeff Hawkins
Empirical evidence demonstrates that every region of the neocortex represents information using sparse activity patterns.