Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userTraining Sparse Neural Network by Constraining Synaptic Weight on Unit Lp Sphere
65
0
0.0
(
0
)
Added by
Weipeng Li
Publication date
2021
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
Sparse deep neural networks have shown their advantages over dense models with fewer parameters and higher computational efficiency. Here we demonstrate constraining the synaptic weights on unit Lp-sphere enables the flexibly control of the sparsity with p and improves the generalization ability of neural networks. Firstly, to optimize the synaptic weights constrained on unit Lp-sphere, the parameter optimization algorithm, Lp-spherical gradient descent (LpSGD) is derived from the augmented Empirical Risk Minimization condition, which is theoretically proved to be convergent. To understand the mechanism of how p affects Hoyers sparsity, the expectation of Hoyers sparsity under the hypothesis of gamma distribution is given and the predictions are verified at various p under different conditions. In addition, the semi-pruning and threshold adaptation are designed for topology evolution to effectively screen out important connections and lead the neural networks converge from the initial sparsity to the expected sparsity. Our approach is validated by experiments on benchmark datasets covering a wide range of domains. And the theoretical analysis pave the way to future works on training sparse neural networks with constrained optimization.
rate research
Read More
In this paper, we explore techniques centered around periodic sampling of model weights that provide convergence improvements on gradient update methods (vanilla acs{SGD}, Momentum, Adam) for a variety of vision problems (classification, detection, segmentation). Importantly, our algorithms provide better, faster and more robust convergence and training performance with only a slight increase in computation time. Our techniques are independent of the neural network model, gradient optimization methods or existing optimal training policies and converge in a less volatile fashion with performance improvements that are approximately monotonic. We conduct a variety of experiments to quantify these improvements and identify scenarios where these techniques could be more useful.
Deep Neural Networks (DNNs) have become increasingly popular in computer vision, natural language processing, and other areas. However, training and fine-tuning a deep learning model is computationally intensive and time-consuming. We propose a new method to improve the performance of nearly every model including pre-trained models. The proposed method uses an ensemble approach where the networks in the ensemble are constructed by reassigning model parameter values based on the probabilistic distribution of these parameters, calculated towards the end of the training process. For pre-trained models, this approach results in an additional training step (usually less than one epoch). We perform a variety of analysis using the MNIST dataset and validate the approach with a number of DNN models using pre-trained models on the ImageNet dataset.
The ever-growing computational demands of increasingly complex machine learning models frequently necessitate the use of powerful cloud-based infrastructure for their training. Binary neural networks are known to be promising candidates for on-device inference due to their extreme compute and memory savings over higher-precision alternatives. However, their existing training methods require the concurrent storage of high-precision activations for all layers, generally making learning on memory-constrained devices infeasible. In this paper, we demonstrate that the backward propagation operations needed for binary neural network training are strongly robust to quantization, thereby making on-the-edge learning with modern models a practical proposition. We introduce a low-cost binary neural network training strategy exhibiting sizable memory footprint and energy reductions while inducing little to no accuracy loss vs Courbariaux & Bengios standard approach. These resource decreases are primarily enabled through the retention of activations exclusively in binary format. Against the latter algorithm, our drop-in replacement sees coincident memory requirement and energy consumption drops of 2--6$times$, while reaching similar test accuracy in comparable time, across a range of small-scale models trained to classify popular datasets. We also demonstrate from-scratch ImageNet training of binarized ResNet-18, achieving a 3.12$times$ memory reduction. Such savings will allow for unnecessary cloud offloading to be avoided, reducing latency, increasing energy efficiency and safeguarding privacy.
As an important class of spiking neural networks (SNNs), recurrent spiking neural networks (RSNNs) possess great computational power and have been widely used for processing sequential data like audio and text. However, most RSNNs suffer from two problems. 1. Due to a lack of architectural guidance, random recurrent connectivity is often adopted, which does not guarantee good performance. 2. Training of RSNNs is in general challenging, bottlenecking achievable model accuracy. To address these problems, we propose a new type of RSNNs called Skip-Connected Self-Recurrent SNNs (ScSr-SNNs). Recurrence in ScSr-SNNs is introduced in a stereotyped manner by adding self-recurrent connections to spiking neurons, which implements local memory. The network dynamics is enriched by skip connections between nonadjacent layers. Constructed by simplified self-recurrent and skip connections, ScSr-SNNs are able to realize recurrent behaviors similar to those of more complex RSNNs while the error gradients can be more straightforwardly calculated due to the mostly feedforward nature of the network. Moreover, we propose a new backpropagation (BP) method called backpropagated intrinsic plasticity (BIP) to further boost the performance of ScSr-SNNs by training intrinsic model parameters. Unlike standard intrinsic plasticity rules that adjust the neurons intrinsic parameters according to neuronal activity, the proposed BIP methods optimize intrinsic parameters based on the backpropagated error gradient of a well-defined global loss function in addition to synaptic weight training. Based upon challenging speech and neuromorphic speech datasets including TI46-Alpha, TI46-Digits, and N-TIDIGITS, the proposed ScSr-SNNs can boost performance by up to 2.55% compared with other types of RSNNs trained by state-of-the-art BP methods.
For the present engineering of neural systems, the preparing of extensive scale learning undertakings generally not just requires a huge neural system with a mind boggling preparing process yet additionally troublesome discover a clarification for genuine applications. In this paper, we might want to present the Collaborative Neural Network Group (CNNG). CNNG is a progression of neural systems that work cooperatively to deal with various errands independently in a similar learning framework. It is advanced from a solitary neural system by reflection. Along these lines, in light of various circumstances removed by the calculation, the CNNG can perform diverse techniques when handling the information. The examples of chose methodology can be seen by human to make profound adapting more reasonable. In our execution, the CNNG is joined by a few moderately little neural systems. We give a progression of examinations to assess the execution of CNNG contrasted with other learning strategies. The CNNG is able to get a higher accuracy with a much lower training cost. We can reduce the error rate by 74.5% and reached the accuracy of 99.45% in MNIST with three feedforward networks (4 layers) in one training epoch.
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
