The backpropagation algorithm is an invaluable tool for training artificial neural networks; however, because of a weight sharing requirement, it does not provide a plausible model of brain function. Here, in the context of a two-layer network, we derive an algorithm for training a neural network which avoids this problem by not requiring explicit error computation and backpropagation. Furthermore, our algorithm maps onto a neural network that bears a remarkable resemblance to the connectivity structure and learning rules of the cortex. We find that our algorithm empirically performs comparably to backprop on a number of datasets.
Department of Physiology University of Bern（伯尔尼大学生理学系）；Montreal Institute for Learning Algorithms Université de Montréal（蒙特利尔大学蒙特利尔学习算法研究所）
Animal behaviour depends on learning to associate sensory stimuli with the desired motor command. Understanding how the brain orchestrates the necessary synaptic modifications across different brain areas has remained a longstanding puzzle. Here, we introduce a multi-area neuronal network model in which synaptic plasticity continuously adapts the network towards a global desired output. In this model synaptic learning is driven by a local dendritic prediction error that arises from a failure to predict the top-down input given the bottom-up activities. Such errors occur at apical dendrites of …
Institute of Neuroinformatics（神经信息学研究所）；University of Zürich（苏黎世大学）；ETH Zürich（苏黎世联邦理工学院）；University of Bern（伯尔尼大学）；University of Bristol（布里斯托大学）；Mila（米拉研究所）；Université de Montréal（蒙特利尔大学）
Deep learning has seen remarkable developments over the last years, many of them inspired by neuroscience. However, the main learning mechanism behind these advances - error backpropagation - appears to be at odds with neurobiology. Here, we introduce a multilayer neuronal network model with simplified dendritic compartments in which error-driven synaptic plasticity adapts the network towards a global desired output. In contrast to previous work our model does not require separate phases and synaptic learning is driven by local dendritic prediction errors continuously in time. Such errors orig…
Cortical circuits exhibit intricate recurrent architectures that are remarkably similar across different brain areas. Such stereotyped structure suggests the existence of common computational principles. However, such principles have remained largely elusive. Inspired by gated-memory networks, namely long short-term memory networks (LSTMs), we introduce a recurrent neural network in which information is gated through inhibitory cells that are subtractive (subLSTM). We propose a natural mapping of subLSTMs onto known canonical excitatory-inhibitory cortical microcircuits. Our empirical evaluati…
University of California, Santa Barbara（加州大学圣巴巴拉分校）
Several recent studies attempt to address the biological implausibility of the well-known backpropagation (BP) method. While promising methods such as feedback alignment, direct feedback alignment, and their variants like sign-concordant feedback alignment tackle BP's weight transport problem, their validity remains controversial owing to a set of other unsolved issues. In this work, we answer the question of whether it is possible to realize random backpropagation solely based on mechanisms observed in neuroscience. We propose a hypothetical framework consisting of a new microcircuit architec…
The error-backpropagation (backprop) algorithm remains the most common solution to the credit assignment problem in artificial neural networks. In neuroscience, it is unclear whether the brain could adopt a similar strategy to correctly modify its synapses. Recent models have attempted to bridge this gap while being consistent with a range of experimental observations. However, these models are either unable to effectively backpropagate error signals across multiple layers or require a multi-phase learning process, neither of which are reminiscent of learning in the brain. Here, we introduce a…
Over the past decade there has been a growing interest in the development of parallel hardware systems for simulating large-scale networks of spiking neurons. Compared to other highly-parallel systems, GPU-accelerated solutions have the advantage of a relatively low cost and a great versatility, thanks also to the possibility of using the CUDA-C/C++ programming languages. NeuronGPU is a GPU library for large-scale simulations of spiking neural network models, written in the C++ and CUDA-C++ programming languages, based on a novel spike-delivery algorithm. This library includes simple LIF (leak…
There are several indications that brain is organized not on a basis of individual unreliable neurons, but on a micro-circuital scale providing Lego blocks employed to create complex architectures. At such an intermediate scale, the firing activity in the microcircuits is governed by collective effects emerging by the background noise soliciting spontaneous firing, the degree of mutual connections between the neurons, and the topology of the connections. We compare spontaneous firing activity of small populations of neurons adhering to an engineered scaffold with simulations of biologically pl…
Cortical pyramidal neurons receive inputs from multiple distinct neural populations and integrate these inputs in separate dendritic compartments. We explore the possibility that cortical microcircuits implement Canonical Correlation Analysis (CCA), an unsupervised learning method that projects the inputs onto a common subspace so as to maximize the correlations between the projections. To this end, we seek a multi-channel CCA algorithm that can be implemented in a biologically plausible neural network. For biological plausibility, we require that the network operates in the online setting and…
Harnessing cortical geometry, wiring, and function as inductive biases for recurrent neural networks
Neuromatch Academy, Neuromatch, Inc., USA（Neuromatch学院，Neuromatch公司，美国）；McGovern Institute for Brain Research, Massachusetts Institute of Technology (MIT)（麦戈文脑科学研究所，麻省理工学院（MIT））
University of California, Santa Barbara（加州大学圣塔芭芭拉分校）
Our brain consists of biological neurons encoding information through accurate spike timing, yet both the architecture and learning rules of our brain remain largely unknown. Comparing to the recent development of backpropagation-based (BP-based) methods that are able to train spiking neural networks (SNNs) with high accuracy, biologically plausible methods are still in their infancy. In this work, we wish to answer the question of whether it is possible to attain comparable accuracy of SNNs trained by BP-based rules with bio-plausible mechanisms. We propose a new bio-plausible learning framew…
Heidelberg University（海德堡大学）；University of Bern（伯尔尼大学）
The response time of physical computational elements is finite, and neurons are no exception. In hierarchical models of cortical networks each layer thus introduces a response lag. This inherent property of physical dynamical systems results in delayed processing of stimuli and causes a timing mismatch between network output and instructive signals, thus afflicting not only inference, but also learning. We introduce Latent Equilibrium, a new framework for inference and learning in networks of slow components which avoids these issues by harnessing the ability of biological neurons to phase-adv…
A Bayes-Markov Neuromorphic Model of Cortical Orientation Selectivity: A Computational Re-implementation and Quantitative Simulation Study
Sharif University of Technology（谢里夫理工大学）；University of Tehran（德黑兰大学）；Islamic Azad University（伊斯兰阿扎德大学）；Pasargad Institute for Advanced Innovative Solutions (PIAIS)（帕萨加德高级创新解决方案研究所）
The paper introduces a biologically and evolutionarily plausible neural architecture that allows a single group of neurons, or an entire cortical pathway, to be dynamically reconfigured to perform multiple, potentially very different computations. The paper shows that reconfigurability can account for the observed stochastic and distributed coding behavior of neurons and provides a parsimonious explanation for timing phenomena in psychophysical experiments. It also shows that reconfigurable pathways correspond to classes of statistical classifiers that include decision lists, decision trees, a…
IBM Research - Zurich（IBM苏黎世研究院）；Institute of Neuroinformatics, University of Zurich and ETH Zurich（苏黎世大学与苏黎世联邦理工学院神经信息学研究所）
Plasticity circuits in the brain are known to be influenced by the distribution of the synaptic weights through the mechanisms of synaptic integration and local regulation of synaptic strength. However, the complex interplay of stimulation-dependent plasticity with local learning signals is disregarded by most of the artificial neural network training algorithms devised so far. Here, we propose a novel biologically inspired optimizer for artificial (ANNs) and spiking neural networks (SNNs) that incorporates key principles of synaptic integration observed in dendrites of cortical neurons: GRAPE…
Deep learning has recently led to great successes in tasks such as image recognition (e.g Krizhevsky et al., 2012). However, deep networks are still outmatched by the power and versatility of the brain, perhaps in part due to the richer neuronal computations available to cortical circuits. The challenge is to identify which neuronal mechanisms are relevant, and to find suitable abstractions to model them. Here, we show how aspects of spike timing, long hypothesized to play a crucial role in cortical information processing, could be incorporated into deep networks to build richer, versatile rep…
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Center for Excellence in Brain Science and Intelligence Technology, Chinese Academy of Sciences（中国科学院脑科学与智能技术卓越创新中心）
Spiking Neural Networks (SNNs) contain more biologically realistic structures and biologically-inspired learning principles than those in standard Artificial Neural Networks (ANNs). SNNs are considered the third generation of ANNs, powerful on the robust computation with a low computational cost. The neurons in SNNs are non-differential, containing decayed historical states and generating event-based spikes after their states reaching the firing threshold. These dynamic characteristics of SNNs make it difficult to be directly trained with the standard backpropagation (BP), which is also consid…
Neural networks are complex algorithms that loosely model the behaviour of the human brain. They play a significant role in computational neuroscience and artificial intelligence. The next generation of neural network models is based on the spike timing activity of neurons: spiking neural networks (SNNs). However, model parameters in SNNs are difficult to search and optimise. Previous studies using genetic algorithm (GA) optimisation of SNNs were focused mainly on simple, feedforward, or oscillatory networks, but not much work has been done on optimising cortex-like recurrent SNNs. In this wor…
Flatiron Institute（弗莱迪龙研究所）；Rutgers University（罗格斯大学）；NYU Medical Center（纽约大学医学中心）
To guide behavior, the brain extracts relevant features from high-dimensional data streamed by sensory organs. Neuroscience experiments demonstrate that the processing of sensory inputs by cortical neurons is modulated by instructive signals which provide context and task-relevant information. Here, adopting a normative approach, we model these instructive signals as supervisory inputs guiding the projection of the feedforward data. Mathematically, we start with a family of Reduced-Rank Regression (RRR) objective functions which include Reduced Rank (minimum) Mean Square Error (RRMSE) and Cano…
Brain-inspired learning models attempt to mimic the cortical architecture and computations performed in the neurons and synapses constituting the human brain to achieve its efficiency in cognitive tasks. In this work, we present convolutional spike timing dependent plasticity based feature learning with biologically plausible leaky-integrate-and-fire neurons in Spiking Neural Networks (SNNs). We use shared weight kernels that are trained to encode representative features underlying the input patterns thereby improving the sparsity as well as the robustness of the learning model. We demonstrate…
Neuro-Inspired Visual Pattern Recognition via Biological Reservoir Computing
Institute of Information Science and Technologies of the National Research Council of Italy (ISTI-CNR)（意大利国家研究理事会信息科学与技术研究所）；Institute of Biophysics of the National Research Council of Italy (IBF-CNR)（意大利国家研究理事会生物物理研究所）
University of Arizona（亚利桑那大学）；University of California, Berkeley（加州大学伯克利分校）
Place cells in the hippocampus are active when an animal visits a certain location (referred to as a place field) within an environment. Grid cells in the medial entorhinal cortex (MEC) respond at multiple locations, with firing fields that form a periodic and hexagonal tiling of the environment. The joint activity of grid and place cell populations, as a function of location, forms a neural code for space. An ensemble of codes is generated by varying grid and place cell population parameters. For each code in this ensemble, codewords are generated by stimulating a network with a discrete set …
