Loihi: A Neuromorphic Manycore Processor with On-Chip Learning

Davies, Mike; Srinivasa, Narayan; Lin, Tsung-Han; Chinya, Gautham N.; Cao, Yongqiang; Choday, Sri Harsha; Dimou, Georgios; Joshi, Prasad; Imam, Nabil; Jain, Shweta; Liao, Yuan; Lin, Chit-Kwan; Lines, Andrew; Liu, Ruokun; Mathaikutty, Deepak; McCoy, Steven; Paul, Arnab; Tse, Jonathan; Venkataramanan, Guruguhanathan; Weng, Yi-Hsin; Wild, Andreas; Yang, Young-Kyu; Wang, Hong

doi:10.1109/mm.2018.112130359

Cited by 2,787 publications

(1,949 citation statements)

References 12 publications

Supporting

Mentioning

1,942

Contrasting

Unclassified

Order By: Relevance

“…The previously described learning dilemma for RSNNs also affects the development of new, brain inspired computing hardware, which aims at a drastic reduction in the energy consumption of computing and learning. Resulting new designs of computer chips, such as Intel's Loihi (Davies et al, 2018), are usually focused on RSNN architectures. On-chip learning capability for these RSNNs in the hardware is essential.…”

Section: Introductionmentioning

confidence: 99%

A solution to the learning dilemma for recurrent networks of spiking neurons

Bellec

Scherr

Subramoney

et al. 2019

Preprint

View full text Add to dashboard Cite

Recurrently connected networks of spiking neurons underlie the astounding information processing capabilities of the brain. But in spite of extensive research, it has remained open how learning through synaptic plasticity could be organized in such networks. We argue that two pieces of this puzzle were provided by experimental data from neuroscience. A new mathematical insight tells us how they need to be combined to enable network learning through gradient descent. The resulting learning method -called e-prop -approaches the performance of BPTT (backpropagation through time), the best known method for training recurrent neural networks in machine learning. But in contrast to BPTT, e-prop is biologically plausible. In addition, it elucidates how brain-inspired new computer chips -that are drastically more energy efficient -can be enabled to learn.

show abstract

Section: Introductionmentioning

confidence: 99%

A solution to the learning dilemma for recurrent networks of spiking neurons

Bellec

Scherr

Subramoney

et al. 2019

Preprint

View full text Add to dashboard Cite

show abstract

“…By combining the strengths of modern VLSI technology and mimicking the principle of the biological brain, neuromorphic machines are potentially more powerful in managing high‐dimensionality and unstructured data while operating with much lower power consumption. Currently, commercial neuromorphic systems are mostly built on complementary CMOS circuits, including TrueNorth by IBM, SpiNNaker by the University of Manchester, Neurogrid by Stanford University, Loihi by Intel, and Tianjic by Tsinghua University . Compared to conventional processors based on Von Neumann architecture, these neuromorphic chips exhibit an exceptional information processing capability at much lower power consumption levels, especially for unstructured data (Figure d).…”

Section: Current State Of Memristive Systems For Neuromorphic Computingmentioning

confidence: 99%

Artificial Perception Built on Memristive System: Visual, Auditory, and Tactile Sensations

Zhao

Tan

et al. 2020

Advanced Intelligent Systems

View full text Add to dashboard Cite

The widespread implementation and rapid development of autonomous systems pose stringent performance requirements on emerging sensory systems. In addition to the basic sensing requirements, leading sensory systems are required to process data and extract featured information from highly redundant data in real time. With the added edge‐computational capabilities, data shuttling is avoided, leading to significant reduction of computational burden and bandwidth pressure in the cloud. Among the different computing architectures, the neuromorphic sensory system stands out due to its high power efficiency, low latency, and excellent processing capability. Mimicking the biological neural network, the colocation of sensory, processor, and memory components of neuromorphic sensory systems enables the requirements for frequent data shuttles to be circumvented. In particular, artificial intelligent perceptions built on memristive neuromorphic systems exhibit outstanding characteristics of small footprint, low power consumption, 3D stacking ability, and high density. Herein, the two essential parts of the memristive artificial perceptron system are presented: 1) memristive systems for neuromorphic computing and 2) high‐performance sensors. Next, the current state of the art established on artificial perceptron systems covering visual, auditory, and tactile sensations is highlighted. To conclude, the current challenges and future direction in the area of advanced intelligent perceptions are presented.

show abstract

“…In generalized threshold models like the Spike Response Model [13], the membrane voltage is given using response kernels that accurately model the post-synaptic responses due to pre-synaptic input spikes, external driving currents and the shape of the spike -the latter term being also used to model refractoriness. However, in simpler adaptations of spiking neuron models, the spike shape is often disregarded, and the membrane potentials are written as simple linear post-synaptic integrations of input spikes and external currents [14,15]. Such a spiking neural network model is shown in Fig.…”

Section: Remapping Synaptic Interactions In a Standard Spiking Networkmentioning

confidence: 99%

“…As long as v i < 1, g i (v n ) → 0, which from (14) leads to the following response for the i-th neuron…”

Section: Growth Transform Non-spiking Neuron Modelmentioning

confidence: 99%

A Spiking Neuron and Population Model based on the Growth Transform Dynamical System

Gangopadhyay

Mehta

Chakrabartty

2019

Preprint

View full text Add to dashboard Cite

AbstractIn neuromorphic engineering, neural populations are generally modeled in a bottom-up manner, where individual neuron models are connected through synapses to form large-scale spiking networks. Alternatively, a top-down approach treats the process of spike generation and neural representation of excitation in the context of minimizing some measure of network energy. However, these approaches usually define the energy functional in terms of some statistical measure of spiking activity (ex. firing rates), which does not allow independent control and optimization of neurodynamical parameters. In this paper, we introduce a new spiking neuron and population model where the dynamical and spiking responses of neurons can be derived directly from a network objective or energy functional of continuous-valued neural variables like the membrane potential. The key advantage of the model is that it allows for independent control over three neuro-dynamical properties: (a) control over the steady-state population dynamics that encodes the minimum of an exact network energy functional; (b) control over the shape of the action potentials generated by individual neurons in the network without affecting the network minimum; and (c) control over spiking statistics and transient population dynamics without affecting the network minimum or the shape of action potentials. At the core of the proposed model are different variants of Growth Transform dynamical systems that produce stable and interpretable population dynamics, irrespective of the network size and the type of neuronal connectivity (inhibitory or excitatory). In this paper, we present several examples where the proposed model has been configured to produce different types of single-neuron dynamics as well as population dynamics. In one such example, the network is shown to adapt such that it encodes the steady-state solution using a reduced number of spikes upon convergence to the optimal solution. In this paper we use this network to construct a spiking associative memory that uses fewer spikes compared to conventional architectures, while maintaining high recall accuracy at high memory loads.

show abstract

Loihi: A Neuromorphic Manycore Processor with On-Chip Learning

Cited by 2,787 publications

References 12 publications

A solution to the learning dilemma for recurrent networks of spiking neurons

A solution to the learning dilemma for recurrent networks of spiking neurons

Artificial Perception Built on Memristive System: Visual, Auditory, and Tactile Sensations

A Spiking Neuron and Population Model based on the Growth Transform Dynamical System

Contact Info

Product

Resources

About