Neural Network has been successfully applied to many real-world problems, such as image recognition and machine translation. However, for the current architecture of neural networks, it is hard to perform complex cognitive tasks, for example, to process the image and audio inputs together. Cortex, as an important architecture in the brain, is important for animals to perform the complex cognitive task. We view the architecture of Cortex in the brain as a missing part in the design of the current artificial neural network. In this paper, we purpose Cortex Neural Network (CrtxNN). The Cortex Neural Network is an upper architecture of neural networks which motivated from cerebral cortex in the brain to handle different tasks in the same learning system. It is able to identify different tasks and solve them with different methods. In our implementation, the Cortex Neural Network is able to process different cognitive tasks and perform reflection to get a higher accuracy. We provide a series of experiments to examine the capability of the cortex architecture on traditional neural networks. Our experiments proved its ability on the Cortex Neural Network can reach accuracy by 98.32% on MNIST and 62% on CIFAR10 at the same time, which can promisingly reduce the loss by 40%.
Center for Brains, Minds, and Machines（脑、心智与机器中心）；McGovern Institute for Brain Research（麦戈文脑科学研究所）；Massachusetts Institute of Technology（麻省理工学院）
We discuss relations between Residual Networks (ResNet), Recurrent Neural Networks (RNNs) and the primate visual cortex. We begin with the observation that a special type of shallow RNN is exactly equivalent to a very deep ResNet with weight sharing among the layers. A direct implementation of such a RNN, although having orders of magnitude fewer parameters, leads to a performance similar to the corresponding ResNet. We propose 1) a generalization of both RNN and ResNet architectures and 2) the conjecture that a class of moderately deep RNNs is a biologically-plausible model of the ventral str…
Recently DCNN (Deep Convolutional Neural Network) has been advocated as a general and promising modelling approach for neural object representation in primate inferotemporal cortex. In this work, we show that some inherent non-uniqueness problem exists in the DCNN-based modelling of image object representations. This non-uniqueness phenomenon reveals to some extent the theoretical limitation of this general modelling approach, and invites due attention to be taken in practice.
Northeastern University（东北大学）；Technical University of Catalonia（加泰罗尼亚理工大学）；Duke University（杜克大学）
A deep neural network (DNN) that can reliably model muscle responses from corresponding brain stimulation has the potential to increase knowledge of coordinated motor control for numerous basic science and applied use cases. Such cases include the understanding of abnormal movement patterns due to neurological injury from stroke, and stimulation based interventions for neurological recovery such as paired associative stimulation. In this work, potential DNN models are explored and the one with the minimum squared errors is recommended for the optimal performance of the M2M-Net, a network that …
Brain Research Institute, UZH（苏黎世大学脑研究所）；National Institutes of Health（美国国立卫生研究院）；Allen Brain Institute（艾伦脑研究所）
Finding a code to unravel the population of neural responses that leads to a distinct animal behavior has been a long-standing question in the field of neuroscience. With the recent advances in machine learning, it is shown that the hierarchically Deep Neural Networks (DNNs) perform optimally in decoding unique features out of complex datasets. In this study, we utilize the power of a DNN to explore the computational principles in the mammalian brain by exploiting the Neuropixel data from Allen Brain Institute. We decode the neural responses from mouse visual cortex to predict the presented st…
Exploring and establishing artificial neural networks with electrophysiological characteristics and high computational efficiency is a popular topic in the field of computer vision. Inspired by the working mechanism of primary visual cortex, pulse-coupled neural network (PCNN) can exhibit the characteristics of synchronous oscillation, refractory period, and exponential decay. However, electrophysiological evidence shows that the neurons exhibit highly complex non-linear dynamics when stimulated by external periodic signals. This chaos phenomenon, also known as the " butterfly effect", cannot …
University of California, Los Angeles（加州大学洛杉矶分校）；New York University（纽约大学）；Duke University（杜克大学）
This paper considers the problem of neural decoding from parallel neural measurements systems such as micro-electrocorticography ($μ$-ECoG). In systems with large numbers of array elements at very high sampling rates, the dimension of the raw measurement data may be large. Learning neural decoders for this high-dimensional data can be challenging, particularly when the number of training samples is limited. To address this challenge, this work presents a novel neural network decoder with a low-rank structure in the first hidden layer. The low-rank constraints dramatically reduce the number of …
An FPGA-based Massively Parallel Neuromorphic Cortex Simulator
本文提出了一种大规模并行和可扩展的神经形态皮层模拟器，旨在模拟大型和结构连接的脉冲神经网络，如复杂的模型的各个领域的皮层。这项工作的主要新颖之处是抽象的神经形态架构成集群所代表的minicolumns和hypercolumns，类似于神经生物学中观察到的基本结构单位。如果没有这种方法，模拟大规模的全连接网络需要非常大的内存来存储点对点连接的查找表。相反，我们使用一种新的架构，基于新皮层中的结构连接，这样所有需要的参数和连接都可以存储在片上存储器中。通过对存储器进行编程，在不改变硬件结构的情况下，可以很容易地对皮层模拟器进行重新配置，以模拟不同的神经网络。分层通信方案允许一个神经元具有多达20万个神经元的扇出。作为概念验证，在一个Altera Stratix V FPGA上的实现能够实时的模拟2000万到26亿个泄漏积分激发（LIF）神经元。我们通过模拟简化的听觉皮层（具有1亿个神经元）来验证该系统。该皮层模拟器实现了每个神经元1.62 μW的低功耗。随着商用FPGA板的出现，我们的系统为大规模脉冲神经网络的设计、实时仿真和分析提供了一个可访问和可扩展的工具。
ETIS Lab, UMR8051, CY Cergy Paris University, ENSEA, CNRS（ETIS实验室，UMR8051，塞尔吉巴黎大学，ENSEA，法国国家科学研究中心）
In order to keep trace of information and grow up, the infant brain has to resolve the problem about where old information is located and how to index new ones. We propose that the immature prefrontal cortex (PFC) use its primary functionality of detecting hierarchical patterns in temporal signals as a second purpose to organize the spatial ordering of the cortical networks in the developing brain itself. Our hypothesis is that the PFC detects the hierarchical structure in temporal sequences in the form of ordinal patterns and use them to index information hierarchically in different parts of …
Department of Applied Physics Stanford（斯坦福大学应用物理系）；Google Brain（谷歌大脑）
The visual system is hierarchically organized to process visual information in successive stages. Neural representations vary drastically across the first stages of visual processing: at the output of the retina, ganglion cell receptive fields (RFs) exhibit a clear antagonistic center-surround structure, whereas in the primary visual cortex, typical RFs are sharply tuned to a precise orientation. There is currently no unified theory explaining these differences in representations across layers. Here, using a deep convolutional neural network trained on image recognition as a model of the visua…
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…
Sensory predictions by the brain in all modalities take place as a result of bottom-up and top-down connections both in the neocortex and between the neocortex and the thalamus. The bottom-up connections in the cortex are responsible for learning, pattern recognition, and object classification, and have been widely modelled using artificial neural networks (ANNs). Here, we present a neural network architecture modelled on the top-down corticothalamic connections and the behaviour of the thalamus: a corticothalamic neural network (CTNN), consisting of an auto-encoder connected to a difference e…
Northwestern University（西北大学）；Shirley Ryan Ability Lab（雪莉·瑞安能力实验室）；University Tübingen（图宾根大学）；Baylor College of Medicine（贝勒医学院）
In recent years, artificial neural networks have achieved state-of-the-art performance for predicting the responses of neurons in the visual cortex to natural stimuli. However, they require a time consuming parameter optimization process for accurately modeling the tuning function of newly observed neurons, which prohibits many applications including real-time, closed-loop experiments. We overcome this limitation by formulating the problem as $K$-shot prediction to directly infer a neuron's tuning function from a small set of stimulus-response pairs using a Neural Process. This required us to …
Systems Design Engineering & Center for Theoretical Neuroscience University of Waterloo（滑铁卢大学系统设计工程与理论神经科学中心）；School of Engineering, University of Guelph（圭尔夫大学工程学院）；Vector Institute for Artificial Intelligence（向量人工智能研究所）；Canadian Institute for Advanced Research（加拿大高级研究学院）；University of Guelph（圭尔夫大学）；University of Waterloo（滑铁卢大学）
Neurons in the visual cortex are correlated in their variability. The presence of correlation impacts cortical processing because noise cannot be averaged out over many neurons. In an effort to understand the functional purpose of correlated variability, we implement and evaluate correlated noise models in deep convolutional neural networks. Inspired by the cortex, correlation is defined as a function of the distance between neurons and their selectivity. We show how to sample from high-dimensional correlated distributions while keeping the procedure differentiable, so that back-propagation ca…
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））
Fault-Tolerant Neural Networks from Biological Error Correction Codes
Center for Theoretical Physics, Massachusetts Institute of Technology（麻省理工学院理论物理中心）；Department of Physics, Massachusetts Institute of Technology（麻省理工学院物理系）；Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology（麻省理工学院电气工程与计算机科学系）
