Opportunities for neuromorphic computing algorithms and applications

Schuman, Catherine D.; Kulkarni, Shruti; Parsa, Maryam; Mitchell, J. Parker; Date, Prasanna; Kay, Bill

doi:10.1038/s43588-021-00184-y

Cited by 480 publications

(243 citation statements)

References 114 publications

Supporting

Mentioning

243

Contrasting

Order By: Relevance

“…Thus, hardware-based ANN algorithms for learning and operating have been implemented based on memristors. They can significantly improve the parameters of neuromorphic computing systems, which have been actively developed in recent years due to new applications, algorithms, and element base ( Indiveri et al, 2011 ; Schuman et al, 2022 ).…”

Section: The Memristive Architecture Enables the Implementation Of Re...mentioning

confidence: 99%

Toward Reflective Spiking Neural Networks Exploiting Memristive Devices

Makarov

Lobov

Shchanikov

et al. 2022

Front. Comput. Neurosci.

View full text Add to dashboard Cite

The design of modern convolutional artificial neural networks (ANNs) composed of formal neurons copies the architecture of the visual cortex. Signals proceed through a hierarchy, where receptive fields become increasingly more complex and coding sparse. Nowadays, ANNs outperform humans in controlled pattern recognition tasks yet remain far behind in cognition. In part, it happens due to limited knowledge about the higher echelons of the brain hierarchy, where neurons actively generate predictions about what will happen next, i.e., the information processing jumps from reflex to reflection. In this study, we forecast that spiking neural networks (SNNs) can achieve the next qualitative leap. Reflective SNNs may take advantage of their intrinsic dynamics and mimic complex, not reflex-based, brain actions. They also enable a significant reduction in energy consumption. However, the training of SNNs is a challenging problem, strongly limiting their deployment. We then briefly overview new insights provided by the concept of a high-dimensional brain, which has been put forward to explain the potential power of single neurons in higher brain stations and deep SNN layers. Finally, we discuss the prospect of implementing neural networks in memristive systems. Such systems can densely pack on a chip 2D or 3D arrays of plastic synaptic contacts directly processing analog information. Thus, memristive devices are a good candidate for implementing in-memory and in-sensor computing. Then, memristive SNNs can diverge from the development of ANNs and build their niche, cognitive, or reflective computations.

show abstract

Section: The Memristive Architecture Enables the Implementation Of Re...mentioning

confidence: 99%

Toward Reflective Spiking Neural Networks Exploiting Memristive Devices

Makarov

Lobov

Shchanikov

et al. 2022

Front. Comput. Neurosci.

View full text Add to dashboard Cite

show abstract

“…Spiking Neural Networks (SNNs) transfer binary and asynchronous information through networks in a low-power manner [63,11,12,52,64,43,68,78]. The major difference of SNNs from standard ANNs is using a Leak-Integrate-and-Fire (LIF) neuron [30] as a non-linear activation.…”

Section: Spiking Neural Networkmentioning

confidence: 99%

Exploring Lottery Ticket Hypothesis in Spiking Neural Networks

Kim¹,

Li²,

Park³

et al. 2022

Preprint

View full text Add to dashboard Cite

Spiking Neural Networks (SNNs) have recently emerged as a new generation of low-power deep neural networks, which is suitable to be implemented on low-power mobile/edge devices. As such devices have limited memory storage, neural pruning on SNNs has been widely explored in recent years. Most existing SNN pruning works focus on shallow SNNs (2∼6 layers), however, deeper SNNs (≥16 layers) are proposed by state-of-the-art SNN works, which is difficult to be compatible with the current SNN pruning work. To scale up a pruning technique towards deep SNNs, we investigate Lottery Ticket Hypothesis (LTH) which states that dense networks contain smaller subnetworks (i.e., winning tickets) that achieve comparable performance to the dense networks. Our studies on LTH reveal that the winning tickets consistently exist in deep SNNs across various datasets and architectures, providing up to 97% sparsity without huge performance degradation. However, the iterative searching process of LTH brings a huge training computational cost when combined with the multiple timesteps of SNNs. To alleviate such heavy searching cost, we propose Early-Time (ET) ticket where we find the important weight connectivity from a smaller number of timesteps. The proposed ET ticket can be seamlessly combined with a common pruning techniques for finding winning tickets, such as Iterative Magnitude Pruning (IMP) and Early-Bird (EB) tickets. Our experiment results show that the proposed ET ticket reduces search time by up to 38% compared to IMP or EB methods. Code is available at Github.

show abstract

“…Neuromorphic vision sensors are generally appropriately designed for neuromorphic vision computing tasks, such as denoising, edge enhancement, spectral filtering, and the recognition of visual information. Depending on whether in situ pre-processing is possible, the approaches can be divided into methods using near-sensor and in-sensor computing processors [ 5 ]. In a near-sensor computing method, the image sensor for capturing visual information and in-memory computing processor for pre-processing the captured image exist separately.…”

Section: Introductionmentioning

confidence: 99%

Progress of Materials and Devices for Neuromorphic Vision Sensors

Cho

Jo²,

Kim³

et al. 2022

Nano-Micro Lett.

View full text Add to dashboard Cite

The latest developments in bio-inspired neuromorphic vision sensors can be summarized in 3 keywords: smaller, faster, and smarter. (1) Smaller: Devices are becoming more compact by integrating previously separated components such as sensors, memory, and processing units. As a prime example, the transition from traditional sensory vision computing to in-sensor vision computing has shown clear benefits, such as simpler circuitry, lower power consumption, and less data redundancy. (2) Swifter: Owing to the nature of physics, smaller and more integrated devices can detect, process, and react to input more quickly. In addition, the methods for sensing and processing optical information using various materials (such as oxide semiconductors) are evolving. (3) Smarter: Owing to these two main research directions, we can expect advanced applications such as adaptive vision sensors, collision sensors, and nociceptive sensors. This review mainly focuses on the recent progress, working mechanisms, image pre-processing techniques, and advanced features of two types of neuromorphic vision sensors based on near-sensor and in-sensor vision computing methodologies. "Image missing"

show abstract

Opportunities for neuromorphic computing algorithms and applications

Cited by 480 publications

References 114 publications

Toward Reflective Spiking Neural Networks Exploiting Memristive Devices

Toward Reflective Spiking Neural Networks Exploiting Memristive Devices

Exploring Lottery Ticket Hypothesis in Spiking Neural Networks

Progress of Materials and Devices for Neuromorphic Vision Sensors

Contact Info

Product

Resources

About