Composing neural algorithms with Fugu

Aimone, James B.; Severa, William; Vineyard, Craig Michael

doi:10.1145/3354265.3354268

Cited by 17 publications

(11 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With Loihi's promising results and the broad space of possibility that these open up, soon, one of the most pressing problems facing the neuromorphic field will be its fragmented and noncomposable collection of programming models and frameworks. While a number of SNN development frameworks have been released for use, they all generally fall into one of three categories: point tools for optimizing SNN parameters with supervised training, usually with deep learning techniques (SNN Conversion Toolbox [21], SLAYER [22], Whetstone [138], and EONS [139]), SNN simulators for conventional architectures that offer low-level programming APIs (Brian 2 [140], BindsNET [141]), or low-level interfaces and runtime frameworks for configuring neuromorphic hardware (PyNN [142], Fugu [143], and our own NxSDK). While the increasing level of exploration and activity in this space is encouraging, none of these frameworks yet present compelling new programming abstractions that are composable and span a wide diversity of algorithms understudy in the field, such as those that are covered by the examples in this survey.…”

Section: F Programming Modelmentioning

confidence: 99%

Advancing Neuromorphic Computing With Loihi: A Survey of Results and Outlook

et al. 2021

View full text Add to dashboard Cite

Deep artificial neural networks apply principles of the brain's information processing that led to breakthroughs in machine learning spanning many problem domains. Neuromorphic computing aims to take this a step further to chips more directly inspired by the form and function of biological neural circuits, so they can process new knowledge, adapt, behave, and learn in real time at low power levels. Despite several decades of research, until recently, very few published results have shown that today's neuromorphic chips can demonstrate quantitative computational value. This is now changing with the advent of Intel's Loihi, a neuromorphic research processor designed to support a broad range of spiking neural networks with sufficient scale, performance, and features to deliver competitive results compared to state-of-the-art contemporary computing architectures. This survey reviews results that are obtained to date with Loihi across the major algorithmic domains under study, including deep learning approaches and novel approaches that aim to more directly harness the key features of spike-based neuromorphic hardware. While conventional feedforward deep neural networks show modest if any benefit on Loihi, more brain-inspired networks using recurrence, precise spike-timing relationships, synaptic plasticity, stochasticity, and sparsity perform certain computation with orders of magnitude lower latency and energy compared to state-of-the-art conventional approaches. These compelling neuromorphic networks solve a diverse range of problems representative of brain-like computation, such as event-based

show abstract

Section: F Programming Modelmentioning

confidence: 99%

Advancing Neuromorphic Computing With Loihi: A Survey of Results and Outlook

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Since I/O will likely continue to be a limiting factor, further processing of simulation outputs on the neuromorphic substrate is likely ideal. One way to do this is to implement the post-processing steps that we performed o ine as neural circuits themselves and integrate them into a fully composed simulation [3].…”

Section: Discussionmentioning

confidence: 99%

Solving a steady-state PDE using spiking networks and neuromorphic hardware

Darby¹,

Severa²,

Hill³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

e widely parallel, spiking neural networks of neuromorphic processors can enable computationally powerful formulations. While recent interest has focused on primarily machine learning tasks, the space of appropriate applications is wide and continually expanding. Here, we leverage the parallel and event-driven structure to solve a steady state heat equation using a random walk method.e random walk can be executed fully within a spiking neural network using stochastic neuron behavior, and we provide results from both IBM TrueNorth and Intel Loihi implementations. Additionally, we position this algorithm as a potential scalable benchmark for neuromorphic systems.

show abstract

“…For example, Fugu [17] sought to achieve a programming platform to enable the development of neuromorphic applications without substantial knowledge of the substrate. Rather than necessitating a developer attain intricate knowledge of how to program and exploit spiking neural dynamics to utilize the potential benefits of neuromorphic computing, Fugu is designed to provide a higher level abstraction as a hardware-independent mechanism for linking a variety of scalable spiking neural algorithms from a variety of sources.…”

Section: Softwarementioning

confidence: 99%

“…To a large extent, one sentence from Ref. [17] of Fugu can illustrate the dilemma faced by such software frameworks: "We envision that as these hardwarespecific interfaces begin to stabilize ".…”

Section: Softwarementioning

confidence: 99%

“…Meanwhile, there have been some efforts to achieve "general purpose" development frameworks for braininspired computing, such as STICK [16] , FUGU [17] , etc., with the goal of providing a high-level programming abstraction and realizing a unified development tool independent of specific chips, i.e., they intend to make hardware specifications/constraints "transparent" to application development. But the problem of not being able to determine whether the hardware is functional enough, i.e., complete, does persist.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Towards "general purpose" brain-inspired computing system

Zhang

Zheng

2021

Tsinghua Sci. Technol.

View full text Add to dashboard Cite

Brain-inspired computing refers to computational models, methods, and systems, that are mainly inspired by the processing mode or structure of brain. A recent study proposed the concept of "neuromorphic completeness" and the corresponding system hierarchy, which is helpful to determine the capability boundary of brain-inspired computing system and to judge whether hardware and software of brain-inspired computing are compatible with each other. As a position paper, this article analyzes the existing brain-inspired chips design characteristics and the current so-called "general purpose" application development frameworks for brain-inspired computing, as well as introduces the background and the potential of this proposal. Further, some key features of this concept are presented through the comparison with the Turing completeness and approximate computation, and the analyses of the relationship with "general-purpose" brain-inspired computing systems (it means that computing systems can support all computable applications). In the end, a promising technical approach to realize such computing systems is introduced, as well as the on-going research and the work foundation. We believe that this work is conducive to the design of extensible neuromorphic complete hardware-primitives and the corresponding chips. On this basis, it is expected to gradually realize "general purpose" brain-inspired computing system, in order to take into account the functionality completeness and application efficiency.

show abstract

Composing neural algorithms with Fugu

Cited by 17 publications

References 9 publications

Advancing Neuromorphic Computing With Loihi: A Survey of Results and Outlook

Advancing Neuromorphic Computing With Loihi: A Survey of Results and Outlook

Solving a steady-state PDE using spiking networks and neuromorphic hardware

Towards "general purpose" brain-inspired computing system

Contact Info

Product

Resources

About