SpiNNaker

Plana, Luis A.; Clark, David; Davidson, Simon; Furber, Steve; Garside, Jim; Painkras, Eustace; Pepper, Jeffrey; Temple, Steve; Bainbridge, J.

doi:10.1145/2043643.2043647

Cited by 35 publications

(7 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hardware platforms for spiking neural network computations have advantages over software simulations in terms of performance and power consumption. For example, SpiNNaker (Plana et al, 2011) combines cheap, generic, yet dedicated CPU boards together to create a powerful SNN simulation framework in hardware. Other platforms (e.g., TrueNorth Akopyan et al, 2015, HRL, and Braindrop) involve the design of a new chip.…”

Section: Discussionmentioning

confidence: 99%

“…is an open source project, written in Python, and supports a (Abadi et al, 2015) backend to improve simulation speed and exploit some limited ML functionality. It also has options for deploying neural models on dedicated hardware platforms; e.g., SpiNNaker (Plana et al, 2011). (Beyeler et al, 2015) and (Fidjeland et al, 2009) also focus on the high-level aspects of SNNs and are thus good candidates for applications in machine learning.…”

Section: Review Of Snn Software Packagesmentioning

confidence: 99%

See 1 more Smart Citation

BindsNET: A Machine Learning-Oriented Spiking Neural Networks Library in Python

Hazan¹,

Saunders²,

Khan³

et al. 2018

Front. Neuroinform.

211

124

View full text Add to dashboard Cite

The development of spiking neural network simulation software is a critical component enabling the modeling of neural systems and the development of biologically inspired algorithms. Existing software frameworks support a wide range of neural functionality, software abstraction levels, and hardware devices, yet are typically not suitable for rapid prototyping or application to problems in the domain of machine learning. In this paper, we describe a new Python package for the simulation of spiking neural networks, specifically geared toward machine learning and reinforcement learning. Our software, called 1, enables rapid building and simulation of spiking networks and features user-friendly, concise syntax. is built on the deep neural networks library, facilitating the implementation of spiking neural networks on fast CPU and GPU computational platforms. Moreover, the framework can be adjusted to utilize other existing computing and hardware backends; e.g., and . We provide an interface with the OpenAI library, allowing for training and evaluation of spiking networks on reinforcement learning environments. We argue that this package facilitates the use of spiking networks for large-scale machine learning problems and show some simple examples by using in practice.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Review Of Snn Software Packagesmentioning

confidence: 99%

BindsNET: A Machine Learning-Oriented Spiking Neural Networks Library in Python

Hazan¹,

Saunders²,

Khan³

et al. 2018

Front. Neuroinform.

211

124

View full text Add to dashboard Cite

show abstract

“…The time cost for spiking learning algorithms is rather large and usually executed on parallel computing units, such as FPGA and Memristor. Also develop chips or system-on-chip for spiking neural networks have been used, see SpiNNaker 70 and TrueNorth. 71 The complexity of spiking learning algorithms is much higher than that of other machine learning algorithms.…”

Section: Algorithm Complexity Analysismentioning

confidence: 99%

A Layered Spiking Neural System for Classification Problems

Zhang

Rong

et al. 2022

Int. J. Neur. Syst.

View full text Add to dashboard Cite

Biological brains have a natural capacity for resolving certain classification tasks. Studies on biologically plausible spiking neurons, architectures and mechanisms of artificial neural systems that closely match biological observations while giving high classification performance are gaining momentum. Spiking neural P systems (SN P systems) are a class of membrane computing models and third-generation neural networks that are based on the behavior of biological neural cells and have been used in various engineering applications. Furthermore, SN P systems are characterized by a highly flexible structure that enables the design of a machine learning algorithm by mimicking the structure and behavior of biological cells without the over-simplification present in neural networks. Based on this aspect, this paper proposes a novel type of SN P system, namely, layered SN P system (LSN P system), to solve classification problems by supervised learning. The proposed LSN P system consists of a multi-layer network containing multiple weighted fuzzy SN P systems with adaptive weight adjustment rules. The proposed system employs specific ascending dimension techniques and a selection method of output neurons for classification problems. The experimental results obtained using benchmark datasets from the UCI machine learning repository and MNIST dataset demonstrated the feasibility and effectiveness of the proposed LSN P system. More importantly, the proposed LSN P system presents the first SN P system that demonstrates sufficient performance for use in addressing real-world classification problems.

show abstract

“…The power supply of the SpiNN-3 board is 5V 1A via a 2.1mm DC port. For peripheral connections, the SpiNN-3 board has 2 ports: ports J1 and J2 that are 34way sub-miniature head socket [15]. The pin assignments are shown in Fig.…”

Section: A Spinnakermentioning

confidence: 99%

“…After MCU receives the events from input sensors, MCU will encode the data into packets and send them to SpiNNaker in real-time. There are two types of SpiNNaker packets of different sizes: 40 bits and 72 bits [15]. 'EOP' symbols are placed after each packet to show that the transmission of that packet was completed.…”

Section: Encoding / Decoding Packetsmentioning

confidence: 99%

Interface Board for Robotic Neuromorphic Systems

Russo¹,

Madsen²,

Nikolić³

2022

Preprint

View full text Add to dashboard Cite

<p>Neuromorphic computing is going to be the new standard in low power AI applications. The integration between new neuromorphic hardware and traditional microcontroller is an open challenge. Here we present an interface board and a communication protocol that allows the communication between different devices using a microcontroller unit (Arduino Due) in the middle. Our compact printed circuit board (PCB) board links different devices as a whole system and provides power supply for the entire system using batteries as power source. Specifically, we have connected a Dynamic Vision Sensor (DVS128), SpiNNaker board and a servo motor, creating a platform for intercepting incoming objects. The data rate of the implemented interface board is 24.64k symbols/s and the latency for generating commands is about 11ms. The complete system is run only by batteries making it very suitable for robotic applications. </p>

show abstract

SpiNNaker

Cited by 35 publications

References 11 publications

BindsNET: A Machine Learning-Oriented Spiking Neural Networks Library in Python

BindsNET: A Machine Learning-Oriented Spiking Neural Networks Library in Python

A Layered Spiking Neural System for Classification Problems

Interface Board for Robotic Neuromorphic Systems

Contact Info

Product

Resources

About