Spiking neural networks (SNNs) incorporating biologically plausible neurons hold great promise because of their unique temporal dynamics and energy efficiency. However, SNNs have developed separately ...from artificial neural networks (ANNs), limiting the impact of deep learning advances for SNNs. Here, we present an alternative perspective of the spiking neuron that incorporates its neural dynamics into a recurrent ANN unit called a spiking neural unit (SNU). SNUs may operate as SNNs, using a step function activation, or as ANNs, using continuous activations. We demonstrate the advantages of SNU dynamics through simulations on multiple tasks and obtain accuracies comparable to, or better than, those of ANNs. The SNU concept enables an efficient implementation with in-memory acceleration for both training and inference. We experimentally demonstrate its efficacy for a music-prediction task in an in-memory-based SNN accelerator prototype using 52,800 phase-change memory devices. Our results open up an avenue for broad adoption of biologically inspired neural dynamics in challenging applications and acceleration with neuromorphic hardware.Spiking neural networks and in-memory computing are both promising routes towards energy-efficient hardware for deep learning. Woźniak et al. incorporate the biologically inspired dynamics of spiking neurons into conventional recurrent neural network units and in-memory computing, and show how this allows for accurate and energy-efficient deep learning.
Neuromorphic Hardware Learns to Learn Bohnstingl, Thomas; Scherr, Franz; Pehle, Christian ...
Frontiers in neuroscience,
05/2019, Volume:
13
Journal Article
Peer reviewed
Open access
Hyperparameters and learning algorithms for neuromorphic hardware are usually chosen by hand to suit a particular task. In contrast, networks of neurons in the brain were optimized through extensive ...evolutionary and developmental processes to work well on a range of computing and learning tasks. Occasionally this process has been emulated through genetic algorithms, but these require themselves hand-design of their details and tend to provide a limited range of improvements. We employ instead other powerful gradient-free optimization tools, such as cross-entropy methods and evolutionary strategies, in order to port the function of biological optimization processes to neuromorphic hardware. As an example, we show these optimization algorithms enable neuromorphic agents to learn very efficiently from rewards. In particular, meta-plasticity, i.e., the optimization of the learning rule which they use, substantially enhances reward-based learning capability of the hardware. In addition, we demonstrate for the first time Learning-to-Learn benefits from such hardware, in particular, the capability to extract abstract knowledge from prior learning experiences that speeds up the learning of new but related tasks. Learning-to-Learn is especially suited for accelerated neuromorphic hardware, since it makes it feasible to carry out the required very large number of network computations.
Online Spatio-Temporal Learning in Deep Neural Networks Bohnstingl, Thomas; Wozniak, Stanislaw; Pantazi, Angeliki ...
IEEE transaction on neural networks and learning systems,
11/2023, Volume:
34, Issue:
11
Journal Article
Open access
Biological neural networks are equipped with an inherent capability to continuously adapt through online learning. This aspect remains in stark contrast to learning with error backpropagation through ...time (BPTT) that involves offline computation of the gradients due to the need to unroll the network through time. Here, we present an alternative online learning algorithm ic framework for deep recurrent neural networks (RNNs) and spiking neural networks (SNNs), called online spatio-temporal learning (OSTL). It is based on insights from biology and proposes the clear separation of spatial and temporal gradient components. For shallow SNNs, OSTL is gradient equivalent to BPTT enabling for the first time online training of SNNs with BPTT-equivalent gradients. In addition, the proposed formulation unveils a class of SNN architectures trainable online at low time complexity. Moreover, we extend OSTL to a generic form, applicable to a wide range of network architectures, including networks comprising long short-term memory (LSTM) and gated recurrent units (GRUs). We demonstrate the operation of our algorithm ic framework on various tasks from language modeling to speech recognition and obtain results on par with the BPTT baselines.
Speech Recognition Using Biologically-Inspired Neural Networks Bohnstingl, Thomas; Garg, Ayush; Wozniak, Stanislaw ...
ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP),
2022-May-23
Conference Proceeding
Automatic speech recognition systems (ASR), such as the recurrent neural network transducer (RNN-T), have reached close to human-like performance and are deployed in commercial applications. However, ...their core operations depart from the powerful biological counterpart, the human brain. On the other hand, the current developments in biologically-inspired ASR models lag behind in terms of accuracy and focus primarily on small-scale applications. In this work, we revisit the incorporation of biologically-plausible models into deep learning and enhance their capabilities, by taking inspiration from the brain's diverse neural and synaptic dynamics. In particular, we propose novel deep learning units by introducing neural connectivity concepts emulating the axo-somatic and the axo-axonic synapses and integrate them into the RNN-T architecture. We demonstrate for the first time that such a model can yield performance levels competitive to the state-of-the-art. Moreover, our implementation has a significantly reduced computational cost and a lower latency.
Biologically-inspired spiking neural networks (SNNs) hold great promise to perform demanding tasks in an energy and area-efficient manner. Memristive devices organized in a crossbar array can be used ...to accelerate operations of artificial neural networks (ANNs) while circumventing limitations of traditional computing paradigms. Recent advances have led to the development of neuromorphic accelerators that employ phase-change memory (PCM) devices. We propose an approach to fully unravel the potential of such systems for SNNs by integrating entire layers, including synaptic weights as well as neuronal states, into crossbar arrays. However, the key challenges of such realizations originate from the intrinsic imperfections of the PCM devices that limit their effective precision. Thus, we investigated the impact of these limitations on the performance of SNNs and demonstrate that the synaptic weight and neuronal state realization using 4-bit precision provides a robust network performance. Moreover, we evaluated the scheme for a multi-layer SNN realized using an experimentally verified model of the PCM devices and achieved performance that is comparable to a floating-point 32-bit model.
Recurrent spiking neural networks (SNNs) are inspired by the working principles of biological nervous systems that offer unique temporal dynamics and event-based processing. Recently, the error ...backpropagation through time (BPTT) algorithm has been successfully employed to train SNNs offline, with comparable performance to artificial neural networks (ANNs) on complex tasks. However, BPTT has severe limitations for online learning scenarios of SNNs where the network is required to simultaneously process and learn from incoming data. Specifically, as BPTT separates the inference and update phases, it would require to store all neuronal states for calculating the weight updates backwards in time. To address these fundamental issues, alternative credit assignment schemes are required. Within this context, neuromorphic hardware (NMHW) implementations of SNNs can greatly benefit from in-memory computing (IMC) concepts that follow the brain-inspired collocation of memory and processing, further enhancing their energy efficiency. In this work, we utilize a biologically-inspired local and online training algorithm compatible with IMC, which approximates BPTT, e-prop, and present an approach to support both inference and training of a recurrent SNN using NMHW. To do so, we embed the SNN weights on an in-memory computing NMHW with phase-change memory (PCM) devices and integrate it into a hardware-in-the-loop training setup. We develop our approach with respect to limited precision and imperfections of the analog devices using a PCM-based simulation framework and a NMHW consisting of in-memory computing cores fabricated in 14nm CMOS technology with 256×256 PCM crossbar arrays. We demonstrate that our approach is robust even to 4-bit precision and achieves competitive performance to a floating-point 32-bit realization, while simultaneously equipping the SNN with online training capabilities and exploiting the acceleration benefits of NMHW.
Biological neural networks are equipped with an inherent capability to continuously adapt through online learning. This aspect remains in stark contrast to learning with error backpropagation through ...time (BPTT) applied to recurrent neural networks (RNNs), or recently to biologically-inspired spiking neural networks (SNNs). BPTT involves offline computation of the gradients due to the requirement to unroll the network through time. Online learning has recently regained the attention of the research community, focusing either on approaches that approximate BPTT or on biologically-plausible schemes applied to SNNs. Here we present an alternative perspective that is based on a clear separation of spatial and temporal gradient components. Combined with insights from biology, we derive from first principles a novel online learning algorithm for deep SNNs, called online spatio-temporal learning (OSTL). For shallow networks, OSTL is gradient-equivalent to BPTT enabling for the first time online training of SNNs with BPTT-equivalent gradients. In addition, the proposed formulation unveils a class of SNN architectures trainable online at low time complexity. Moreover, we extend OSTL to a generic form, applicable to a wide range of network architectures, including networks comprising long short-term memory (LSTM) and gated recurrent units (GRU). We demonstrate the operation of our algorithm on various tasks from language modelling to speech recognition and obtain results on par with the BPTT baselines. The proposed algorithm provides a framework for developing succinct and efficient online training approaches for SNNs and in general deep RNNs.
Automatic speech recognition (ASR) is a capability which enables a program to process human speech into a written form. Recent developments in artificial intelligence (AI) have led to high-accuracy ...ASR systems based on deep neural networks, such as the recurrent neural network transducer (RNN-T). However, the core components and the performed operations of these approaches depart from the powerful biological counterpart, i.e., the human brain. On the other hand, the current developments in biologically-inspired ASR models, based on spiking neural networks (SNNs), lag behind in terms of accuracy and focus primarily on small scale applications. In this work, we revisit the incorporation of biologically-plausible models into deep learning and we substantially enhance their capabilities, by taking inspiration from the diverse neural and synaptic dynamics found in the brain. In particular, we introduce neural connectivity concepts emulating the axo-somatic and the axo-axonic synapses. Based on this, we propose novel deep learning units with enriched neuro-synaptic dynamics and integrate them into the RNN-T architecture. We demonstrate for the first time, that a biologically realistic implementation of a large-scale ASR model can yield competitive performance levels compared to the existing deep learning models. Specifically, we show that such an implementation bears several advantages, such as a reduced computational cost and a lower latency, which are critical for speech recognition applications.
Neural networks have become the key technology of artificial intelligence and have contributed to breakthroughs in several machine learning tasks, primarily owing to advances in deep learning applied ...to Artificial Neural Networks (ANNs). Simultaneously, Spiking Neural Networks (SNNs) incorporating biologically-feasible spiking neurons have held great promise because of their rich temporal dynamics and high-power efficiency. However, the developments in SNNs were proceeding separately from those in ANNs, effectively limiting the adoption of deep learning research insights. Here we show an alternative perspective on the spiking neuron that casts it as a particular ANN construct called Spiking Neural Unit (SNU), and a soft SNU (sSNU) variant that generalizes its dynamics to a novel recurrent ANN unit. SNUs bridge the biologically-inspired SNNs with ANNs and provide a methodology for seamless inclusion of spiking neurons in deep learning architectures. Furthermore, SNU enables highly-efficient in-memory acceleration of SNNs trained with backpropagation through time, implemented with the hardware in-the-loop. We apply SNUs to tasks ranging from hand-written digit recognition, language modelling, to music prediction. We obtain accuracy comparable to, or better than, that of state-of-the-art ANNs, and we experimentally verify the efficacy of the in-memory-based SNN realization for the music-prediction task using 52,800 phase-change memory devices. The new generation of neural units introduced in this paper incorporate biologically-inspired neural dynamics in deep learning. In addition, they provide a systematic methodology for training neuromorphic computing hardware. Thus, they open a new avenue for a widespread adoption of SNNs in practical applications.