Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userEvolving and Understanding Sparse Deep Neural Networks using Cosine Similarity
103
0
0.0
(
0
)
Added by
Decebal Constantin Mocanu
Publication date
2019
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
Training sparse neural networks with adaptive connectivity is an active research topic. Such networks require less storage and have lower computational complexity compared to their dense counterparts. The Sparse Evolutionary Training (SET) procedure uses weights magnitude to evolve efficiently the topology of a sparse network to fit the dataset, while enabling it to have quadratically less parameters than its dense counterpart. To this end, we propose a novel approach that evolves a sparse network topology based on the behavior of neurons in the network. More exactly, the cosine similarities between the activations of any two neurons are used to determine which connections are added to or removed from the network. By integrating our approach within the SET procedure, we propose 5 new algorithms to train sparse neural networks. We argue that our approach has low additional computational complexity and we draw a parallel to Hebbian learning. Experiments are performed on 8 datasets taken from various domains to demonstrate the general applicability of our approach. Even without optimizing hyperparameters for specific datasets, the experiments show that our proposed training algorithms usually outperform SET and state-of-the-art dense neural network techniques. The last but not the least, we show that the evolved connectivity patterns of the input neurons reflect their impact on the classification task.
rate research
Read More
Synaptic plasticity is widely accepted to be the mechanism behind learning in the brains 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 architectures is not known. In this paper, we introduce structured and deep similarity matching cost functions, and show how they can be optimized in a gradient-based manner by neural networks with local learning rules. These networks extend Foldiaks Hebbian/Anti-Hebbian network to deep architectures and structured feedforward, lateral and feedback connections. Credit assignment problem is solved elegantly by a factorization of the dual learning objective to synapse specific local objectives. Simulations show that our networks learn meaningful features.
We introduce an all-optical Diffractive Deep Neural Network (D2NN) architecture that can learn to implement various functions after deep learning-based design of passive diffractive layers that work collectively. We experimentally demonstrated the success of this framework by creating 3D-printed D2NNs that learned to implement handwritten digit classification and the function of an imaging lens at terahertz spectrum. With the existing plethora of 3D-printing and other lithographic fabrication methods as well as spatial-light-modulators, this all-optical deep learning framework can perform, at the speed of light, various complex functions that computer-based neural networks can implement, and will find applications in all-optical image analysis, feature detection and object classification, also enabling new camera designs and optical components that can learn to perform unique tasks using D2NNs.
We investigate Turings notion of an A-type artificial neural network. We study a refinement of Turings original idea, motivated by work of Teuscher, Bull, Preen and Copeland. Our A-types can process binary data by accepting and outputting sequences of binary vectors; hence we can associate a function to an A-type, and we say the A-type {em represents} the function. There are two modes of data processing: clamped and sequential. We describe an evolutionary algorithm, involving graph-theoretic manipulations of A-types, which searches for A-types representing a given function. The algorithm uses both mutation and crossover operators. We implemented the algorithm and applied it to three benchmark tasks. We found that the algorithm performed much better than a random search. For two out of the three tasks, the algorithm with crossover performed better than a mutation-only version.
Deep spiking neural networks (SNNs) hold great potential for improving the latency and energy efficiency of deep neural networks through event-based computation. However, training such networks is difficult due to the non-differentiable nature of asynchronous spike events. In this paper, we introduce a novel technique, which treats the membrane potentials of spiking neurons as differentiable signals, where discontinuities at spike times are only considered as noise. This enables an error backpropagation mechanism for deep SNNs, which works directly on spike signals and membrane potentials. Thus, compared with previous methods relying on indirect training and conversion, our technique has the potential to capture the statics of spikes more precisely. Our novel framework outperforms all previously reported results for SNNs on the permutation invariant MNIST benchmark, as well as the N-MNIST benchmark recorded with event-based vision sensors.
Recently published methods enable training of bitwise neural networks which allow reduced representation of down to a single bit per weight. We present a method that exploits ensemble decisions based on multiple stochastically sampled network models to increase performance figures of bitwise neural networks in terms of classification accuracy at inference. Our experiments with the CIFAR-10 and GTSRB datasets show that the performance of such network ensembles surpasses the performance of the high-precision base model. With this technique we achieve 5.81% best classification error on CIFAR-10 test set using bitwise networks. Concerning inference on embedded systems we evaluate these bitwise networks using a hardware efficient stochastic rounding procedure. Our work contributes to efficient embedded bitwise neural networks.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
