Menu
Outside Research
Tue, Aug 01, 2017
Hierarchical Temporal Memory Based Autonomous Agent for Partially Observable Video Game Environments
This Master’s thesis explores the feasibility of a Hierarchical Temporal Memory (HTM) based game agent that can explore its environment and learn rewarding behaviors. The unsupervised agent learns action sequences with respect to a stimulated reward in real time, navigating a procedurally generated 3D environment and modeling the patterns that stream to its visual sensor.
Ali Kaan Sungur
Sun, May 28, 2017
Towards a neuromorphic implementation of hierarchical temporal memory on SpiNNaker
This paper explores the feasibility of implementing Hierarchical Temporal Memory (HTM) on SpiNNaker, a fully programmable energy-efficient neuromorphic many core system. The paper makes a proposal for mapping the HTM model components to the SpiNNaker chip architecture. It also shows a prototypic implementation of this mapping that is successfully evaluated for different sets of model parameters.
Florian Walter, Marwin Sandner, Florian Rcöhrbein and Alois Knoll
Tue, Mar 21, 2017
An Accelerated Analog Neuromorphic Hardware System Emulating NMDA- and Calcium-Based Non-Linear Dendrites
This paper presents an extension of the BrainScaleS accelerated analog neuromorphic hardware model by supporting multicompartment models and non-linear dendrites. Using a 65 nm prototype Application Specific Integrated Circuit (ASIC), the system emulates different spike types observed in cortical pyramidal neurons: NMDA plateau potentials, calcium and sodium spikes. Dendritic NMDA spikes are an important component of HTM theory, and the authors use our paper as a motivation for developing the hardware.
Johannes Schemmel, Laura Kriener, Paul Muller and Karlheinz Meier
Thu, Mar 02, 2017
Hierarchical Temporal Memory on the Automata Processor
The paper introduces a methodology for synthesizing HTMs on the Automata Processor, a “configurable silicon implementation of nondeterministic finite automata, designed for massively parallel pattern matching.” The authors also demonstrate three prediction applications on their model and its potential to achieve 137-446X performance gains over CPUs.
Mateja Putic, A.J. Varshneya and Mircea R. Stan
Mon, Jan 30, 2017
A Mathematical Formalization of Hierarchical Temporal Memory’s Spatial Pooler
The paper covers a key learning component in Hierarchical Temporal Memory (HTM): the spatial pooler. The spatial pooling algorithm is inspired by how the brain processes information and performs predictions on spatiotemporal data. This paper lays out a mathematical framework for it while introducing methods for using it for classification and dimensionality reduction. It also provides empirical evidence that verifies it can be used for feature learning.
James Mnatzaganian, Ernest Fokoué and Dhireesha Kudithipudi
Mon, Dec 12, 2016
Hierarchical Temporal Memory Method for Time-series-based Anomaly Detection
This paper looks at Hierarchical Temporal Memory (HTM) and the characteristics that make it suitable for time-series based anomaly detection: continuous learning, tolerance to noise and generalization. The authors evaluate HTM on real and artificial data sets to show that HTM discovers anomalies in time-series data.
Jia Wu, Weiru Zeng, Zhe Chen and Xue-fei Tang