A semi-holographic hyperdimensional representation system for hardware-friendly cognitive computing

  title={A semi-holographic hyperdimensional representation system for hardware-friendly cognitive computing},
  author={Alexantrou Serb and Ivan Kobyzev and Jinqiao Wang and Themistoklis Prodromakis},
  journal={Philosophical Transactions of the Royal Society A},
One of the main, long-term objectives of artificial intelligence is the creation of thinking machines. To that end, substantial effort has been placed into designing cognitive systems; i.e. systems that can manipulate semantic-level information. A substantial part of that effort is oriented towards designing the mathematical machinery underlying cognition in a way that is very efficiently implementable in hardware. In this work, we propose a ‘semi-holographic’ representation system that can be… Expand
1 Citations
Cognitive Computing in Data-centric Paradigm
The cognitive computing paradigm implies that a system should be able to extract the knowledge from raw data without any human-made algorithm, and discovering the generalized classes of notions is the first step towards a paradigm of artificial analytical thinking. Expand


TrueNorth: Design and Tool Flow of a 65 mW 1 Million Neuron Programmable Neurosynaptic Chip
This work developed TrueNorth, a 65 mW real-time neurosynaptic processor that implements a non-von Neumann, low-power, highly-parallel, scalable, and defect-tolerant architecture, and successfully demonstrated the use of TrueNorth-based systems in multiple applications, including visual object recognition. Expand
Braindrop: A Mixed-Signal Neuromorphic Architecture With a Dynamical Systems-Based Programming Model
Two innovations—sparse encoding through analog spatial convolution and weighted spike-rate summation though digital accumulative thinning—cut digital traffic drastically, reducing the energy Braindrop consumes per equivalent synaptic operation to 381 fJ for typical network configurations. Expand
Hyperdimensional Computing Nanosystem
By exploiting the unique properties of the underlying nanotechnologies, it is shown that HD computing, when implemented with monolithic 3D integration, can be up to 420X more energy-efficient while using 25X less area compared to traditional silicon CMOS implementations. Expand
To build a brain
For all their progress, computers are still pretty unimpressive. Sure, they can pilot aircraft and simulate nuclear reactors. But even our best machines struggle with tasks that we humans find easy,Expand
Holographic reduced representations
  • T. Plate
  • Computer Science, Medicine
  • IEEE Trans. Neural Networks
  • 1995
This paper describes a method for representing more complex compositional structure in distributed representations that uses circular convolution to associate items, which are represented by vectors. Expand
ACT-R: A Theory of Higher Level Cognition and Its Relation to Visual Attention
A demonstration of ACT-R's application to menu selection is discussed and it is shown that theACT-R theory makes unique predictions, without estimating any parameters, about the time to search a menu. Expand
A reconfigurable on-line learning spiking neuromorphic processor comprising 256 neurons and 128K synapses
This paper presents a full-custom mixed-signal VLSI device with neuromorphic learning circuits that emulate the biophysics of real spiking neurons and dynamic synapses for exploring the properties of computational neuroscience models and for building brain-inspired computing systems. Expand
Tensor Product Variable Binding and the Representation of Symbolic Structures in Connectionist Systems
The tensor product representation rests on a principled analysis of structure; it saturates gracefully as larger structures are represented; it permits recursive construction of complex representations from simpler ones; it extends naturally to continuous structures and continuous representational patterns. Expand
Point-to-point connectivity between neuromorphic chips using address events
This paper quantifies tradeoffs faced in allocating bandwidth, granting access, and queuing, as well as throughput requirements, and concludes that an arbitered channel design is the best choice. Expand
Optical implementations of associative networks with versatile adaptive learning capabilities.
The practical issues involved in real optical architectures are analyzed, and actual laboratory optical implementations of associative modules based on Hebbian and Widrow-Hoff learning rules are discussed, including successful experimental demonstrations of their operation. Expand