Fast and energy-efficient neuromorphic deep learning with first-spike times

Abstract

For a biological agent operating under environmental pressure, energy consumption and reaction times are of critical importance. Similarly, engineered systems are optimized for short time-to-solution and low energy-to-solution characteristics. At the level of neuronal implementation, this implies achieving the desired results with as few and as early spikes as possible. With time-to-first-spike coding both of these goals are inherently emerging features of learning.Here, we describe a rigorous derivation of a learning rule for such first-spike times in networks of leaky integrate-andfire neurons, relying solely on input and output spike times, and show how this mechanism can implement error backpropagation in hierarchical spiking networks. Furthermore, we emulate our framework on the BrainScaleS-2 neuromorphic system and demonstrate its capability of harnessing the system's speed and energy characteristics. Finally, we examine how our approach generalizes to other neuromorphic platforms by studying how its performance is affected by typical distortive effects induced by neuromorphic substrates.

Online Course Model of Social and Political Education Using Deep Learning

“…In recent years, deep learning algorithms are a breakthrough in the field of machine learning research [ 9 , 10 ]. At the beginning of the 21st century, Canadian scholars put forward the concept of deep learning and started the research boom of deep learning [ 11 , 12 ]. After years of development, deep learning technology has achieved outstanding performance in the fields of computer vision, natural language processing, and speech recognition [ 13 ].…”

The BrainScaleS-2 Accelerated Neuromorphic System With Hybrid Plasticity

“…• Time-to-first spike (Göltz et al, 2021) • Surrogate-Gradient-Based Learning (Cramer et al, 2022) • Analog ANN training (Weis et al, 2020) They differ in which measurements are necessary and what model of the physical system is used. In the time-to-first spike gradient-based training scheme, which we won't discuss in detail here, the essential idea is that it is possible to compute the derivative of the spike time with respect to input weights based on an analytical expression of the spike time.…”

“…In contrast to the time-to-first spike approach (Göltz et al, 2021 ), this does not require explicit or analytical knowledge of the function t ⋆ ( x, p ) and is also applicable to more complex neuron models. In the context of spiking neural networks, this was recognized by Wunderlich and Pehle ( 2020 ) and elaborated in full generality by Pehle ( 2021 ).…”

Spiking neuromorphic chip learns entangled quantum states

“…Larger system sizes will skew this comparison further to favor of BrainScaleS-2, which can even implement more densely connected network topologies without incurring a performance penalty. We also note that the BrainScaleS-2 chip requires less than 500 mW [37,38], while the Intel Xeon E5-2630v4 has a thermal design power (TDP) of 85 W for 10 cores. As such BrainScaleS-2 is using comparable energy even for the smallest systems we implemented in the prototype system used in the main manuscript.…”