In this paper, we present a new supervised learning algorithm that is based on the Hebbian learning algorithm in an attempt to offer a substitute for back propagation along with the gradient descent for a more biologically plausible method. The best performance for the algorithm was achieved when it was run on a feed-forward neural network with the MNIST handwritten digits data set reaching an accuracy of 70.4% on the test data set and 71.48% on the validation data set.
Similarity Matching Networks: Hebbian Learning and Convergence Over Multiple Time Scales
Department of Information and Electric Engineering and Applied Mathematics, University of Salerno, Italy（信息与电气工程及应用数学系，萨勒诺大学）；Center for Control, Dynamical Systems, and Computation, UC Santa Barbara, CA, USA（控制、动态系统与计算中心，加州大学圣芭芭拉分校）
John A. Paulson School of Engineering and Applied Sciences（约翰·A·保尔森工程与应用科学学院）；Harvard University（哈佛大学）
Synaptic plasticity is widely accepted to be the mechanism behind learning in the brain's neural networks. A central question is how synapses, with access to only local information about the network, can still organize collectively and perform circuit-wide learning in an efficient manner. In single-layered and all-to-all connected neural networks, local plasticity has been shown to implement gradient-based learning on a class of cost functions that contain a term that aligns the similarity of outputs to the similarity of inputs. Whether such cost functions exist for networks with other archite…
Deep learning networks generally use non-biological learning methods. By contrast, networks based on more biologically plausible learning, such as Hebbian learning, show comparatively poor performance and difficulties of implementation. Here we show that Hebbian learning in hierarchical, convolutional neural networks can be implemented almost trivially with modern deep learning frameworks, by using specific losses whose gradients produce exactly the desired Hebbian updates. We provide expressions whose gradients exactly implement a plain Hebbian rule (dw ~= xy), Grossberg's instar rule (dw ~= …
A companion paper introduces a nonlinear network with Hebbian excitatory (E) neurons that are reciprocally coupled with anti-Hebbian inhibitory (I) neurons and also receive Hebbian feedforward excitation from sensory (S) afferents. The present paper derives the network from two normative principles that are mathematically equivalent but conceptually different. The first principle formulates unsupervised learning as a constrained optimization problem: maximization of S-E correlations subject to a copositivity constraint on E-E correlations. A combination of Legendre and Lagrangian duality yield…
Virginia Tech（弗吉尼亚理工大学）；University of Arizona（亚利桑那大学）
Feed-forward deep neural networks have been used extensively in various machine learning applications. Developing a precise understanding of the underling behavior of neural networks is crucial for their efficient deployment. In this paper, we use an information theoretic approach to study the flow of information in a neural network and to determine how entropy of information changes between consecutive layers. Moreover, using the Information Bottleneck principle, we develop a constrained optimization problem that can be used in the training process of a deep neural network. Furthermore, we de…
Emerging NeoHebbian Dynamics in Forward-Forward Learning: Implications for Neuromorphic Computing
DeustoTech, University of Deusto（德乌斯托大学德乌斯托技术中心）；TECNALIA, Basque Research & Technology Alliance (BRTA)（泰克纳利亚，巴斯克研究与技术联盟（BRTA））；University of the Basque Country (UPV/EHU)（巴斯克大学（UPV/EHU））
This paper introduces a rate-based nonlinear neural network in which excitatory (E) neurons receive feedforward excitation from sensory (S) neurons, and inhibit each other through disynaptic pathways mediated by inhibitory (I) interneurons. Correlation-based plasticity of disynaptic inhibition serves to incompletely decorrelate E neuron activity, pushing the E neurons to learn distinct sensory features. The plasticity equations additionally contain "extra" terms fostering competition between excitatory synapses converging onto the same postsynaptic neuron and inhibitory synapses diverging from…
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…
This review explores biologically inspired learning as a model for intelligent robot control and sensing technology on the basis of specific examples. Hebbian synaptic learning is discussed as a functionally relevant model for machine learning and intelligence, as explained on the basis of examples from the highly plastic biological neural networks of invertebrates and vertebrates. Its potential for adaptive learning and control without supervision, the generation of functional complexity, and control architectures based on self organization is brought forward. Learning without prior knowledge…
We propose a simplified model of attention which is applicable to feed-forward neural networks and demonstrate that the resulting model can solve the synthetic "addition" and "multiplication" long-term memory problems for sequence lengths which are both longer and more widely varying than the best published results for these tasks.
We define and establish the conditions for `equivalent neural networks' - neural networks with different weights, biases, and threshold functions that result in the same associated function. We prove that given a neural network $\mathcal{N}$ with piece-wise linear activation, the space of coefficients describing all equivalent neural networks is given by a semialgebraic set. This result is obtained by studying different representations of a given piece-wise linear function using the Tarski-Seidenberg theorem.
Spiking neural networks (SNN) have recently emerged as alternatives to traditional neural networks, owing to energy efficiency benefits and capacity to better capture biological neuronal mechanisms. However, the classic backpropagation algorithm for training traditional networks has been notoriously difficult to apply to SNN due to the hard-thresholding and discontinuities at spike times. Therefore, a large majority of prior work believes exact gradients for SNN w.r.t. their weights do not exist and has focused on approximation methods to produce surrogate gradients. In this paper, (1) by appl…
We propose a new learning framework, signal propagation (sigprop), for propagating a learning signal and updating neural network parameters via a forward pass, as an alternative to backpropagation. In sigprop, there is only the forward path for inference and learning. So, there are no structural or computational constraints necessary for learning to take place, beyond the inference model itself, such as feedback connectivity, weight transport, or a backward pass, which exist under backpropagation based approaches. That is, sigprop enables global supervised learning with only a forward path. Th…
This paper is an extension to the memory retrieval procedure of the B-Matrix approach [6],[17] to neural network learning. The B-Matrix is a part of the interconnection matrix generated from the Hebbian neural network, and in memory retrieval, the B-matrix is clamped with a small fragment of the memory. The fragment gradually enlarges by means of feedback, until the entire vector is obtained. In this paper, we propose the use of delta learning to enhance the retrieval rate of the stored memories.
This paper is dedicated to the long-term, or multi-step-ahead, time series prediction problem. We propose a novel method for training feed-forward neural networks, such as multilayer perceptrons, with tapped delay lines. Special batch calculation of derivatives called Forecasted Propagation Through Time and batch modification of the Extended Kalman Filter are introduced. Experiments were carried out on well-known time series benchmarks, the Mackey-Glass chaotic process and the Santa Fe Laser Data Series. Recurrent and feed-forward neural networks were evaluated.
University of Pretoria（比勒陀利亚大学）；Stellenbosch University；Griffith University（格里菲斯大学）
It has been argued in the past that high-dimensional neural networks do not exhibit local minima capable of trapping an optimisation algorithm. However, the relationship between loss surface modality and the neural architecture parameters, such as the number of hidden neurons per layer and the number of hidden layers, remains poorly understood. This study employs fitness landscape analysis to study the modality of neural network loss surfaces under various feed-forward architecture settings. An increase in the problem dimensionality is shown to yield a more searchable and more exploitable loss…
We introduce Error Forward-Propagation, a biologically plausible mechanism to propagate error feedback forward through the network. Architectural constraints on connectivity are virtually eliminated for error feedback in the brain; systematic backward connectivity is not used or needed to deliver error feedback. Feedback as a means of assigning credit to neurons earlier in the forward pathway for their contribution to the final output is thought to be used in learning in the brain. How the brain solves the credit assignment problem is unclear. In machine learning, error backpropagation is a hi…
We propose a feed-forward inference method applicable to belief and neural networks. In a belief network, the method estimates an approximate factorized posterior of all hidden units given the input. In neural networks the method propagates uncertainty of the input through all the layers. In neural networks with injected noise, the method analytically takes into account uncertainties resulting from this noise. Such feed-forward analytic propagation is differentiable in parameters and can be trained end-to-end. Compared to standard NN, which can be viewed as propagating only the means, we propa…
We show that small and shallow feed-forward neural networks can achieve near state-of-the-art results on a range of unstructured and structured language processing tasks while being considerably cheaper in memory and computational requirements than deep recurrent models. Motivated by resource-constrained environments like mobile phones, we showcase simple techniques for obtaining such small neural network models, and investigate different tradeoffs when deciding how to allocate a small memory budget.
Gulf University for Science and Technology（海湾科技大学）；Kuwait University（科威特大学）
CODEQ is a new, population-based meta-heuristic algorithm that is a hybrid of concepts from chaotic search, opposition-based learning, differential evolution and quantum mechanics. CODEQ has successfully been used to solve different types of problems (e.g. constrained, integer-programming, engineering) with excellent results. In this paper, CODEQ is used to train feed-forward neural networks. The proposed method is compared with particle swarm optimization and differential evolution algorithms on three data sets with encouraging results.
Universität Göttingen（哥廷根大学）；Bernstein Center for Computational Neuroscience（伯恩斯坦计算神经科学中心）
The structure of the majority of modern deep neural networks is characterized by uni- directional feed-forward connectivity across a very large number of layers. By contrast, the architecture of the cortex of vertebrates contains fewer hierarchical levels but many recurrent and feedback connections. Here we show that a small, few-layer artificial neural network that employs feedback will reach top level performance on a standard benchmark task, otherwise only obtained by large feed-forward structures. To achieve this we use feed-forward transfer entropy between neurons to structure feedback co…
There have been several attempts to mathematically understand neural networks and many more from biological and computational perspectives. The field has exploded in the last decade, yet neural networks are still treated much like a black box. In this work we describe a structure that is inherent to a feed forward neural network. This will provide a framework for future work on neural networks to improve training algorithms, compute the homology of the network, and other applications. Our approach takes a more geometric point of view and is unlike other attempts to mathematically understand ne…
Recurrent neural network architectures can have useful computational properties, with complex temporal dynamics and input-sensitive attractor states. However, evaluation of recurrent dynamic architectures requires solution of systems of differential equations, and the number of evaluations required to determine their response to a given input can vary with the input, or can be indeterminate altogether in the case of oscillations or instability. In feed-forward networks, by contrast, only a single pass through the network is needed to determine the response to a given input. Modern machine-lear…
This work is focused on improving the character recognition capability of feed-forward back-propagation neural network by using one, two and three hidden layers and the modified additional momentum term. 182 English letters were collected for this work and the equivalent binary matrix form of these characters was applied to the neural network as training patterns. While the network was getting trained, the connection weights were modified at each epoch of learning. For each training sample, the error surface was examined for minima by computing the gradient descent. We started the experiment b…
We investigate a recently proposed model for cortical computation which performs relational inference. It consists of several interconnected, structurally equivalent populations of leaky integrate-and-fire (LIF) neurons, which are trained in a self-organized fashion with spike-timing dependent plasticity (STDP). Despite its robust learning dynamics, the model is susceptible to a problem typical for recurrent networks which use a correlation based (Hebbian) learning rule: if trained with high learning rates, the recurrent connections can cause strong feedback loops in the network dynamics, whic…
