Abstraction based Output Range Analysis for Neural Networks
- URL: http://arxiv.org/abs/2007.09527v1
- Date: Sat, 18 Jul 2020 22:24:54 GMT
- Title: Abstraction based Output Range Analysis for Neural Networks
- Authors: Pavithra Prabhakar and Zahra Rahimi Afzal
- Abstract summary: We consider the problem of output range analysis for feed-forward neural networks with ReLU activation functions.
Existing approaches reduce the output range analysis problem to satisfiability and optimization solving.
We present a novel abstraction technique that constructs a simpler neural network with fewer neurons.
- Score: 10.051309746913512
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: In this paper, we consider the problem of output range analysis for
feed-forward neural networks with ReLU activation functions. The existing
approaches reduce the output range analysis problem to satisfiability and
optimization solving, which are NP-hard problems, and whose computational
complexity increases with the number of neurons in the network. To tackle the
computational complexity, we present a novel abstraction technique that
constructs a simpler neural network with fewer neurons, albeit with interval
weights called interval neural network (INN), which over-approximates the
output range of the given neural network. We reduce the output range analysis
on the INNs to solving a mixed integer linear programming problem. Our
experimental results highlight the trade-off between the computation time and
the precision of the computed output range.
Related papers
- An analysis of optimization problems involving ReLU neural networks [38.258426534664046]
We study approaches to analyze and improve the run time behavior of mixed-integer programming solvers.
We numerically compare these approaches for three benchmark problems from the literature.
As a major takeaway we observe and quantify a trade-off between the often desired redundancy of neural network models versus the computational costs for solving related optimization problems.
arXiv Detail & Related papers (2025-02-05T09:18:07Z) - Deep-Unrolling Multidimensional Harmonic Retrieval Algorithms on Neuromorphic Hardware [78.17783007774295]
This paper explores the potential of conversion-based neuromorphic algorithms for highly accurate and energy-efficient single-snapshot multidimensional harmonic retrieval.
A novel method for converting the complex-valued convolutional layers and activations into spiking neural networks (SNNs) is developed.
The converted SNNs achieve almost five-fold power efficiency at moderate performance loss compared to the original CNNs.
arXiv Detail & Related papers (2024-12-05T09:41:33Z) - Erasure Coded Neural Network Inference via Fisher Averaging [28.243239815823205]
Erasure-coded computing has been successfully used in cloud systems to reduce tail latency caused by factors such as straggling servers and heterogeneous traffic variations.
We design a method to code over neural networks, that is, given two or more neural network models, how to construct a coded model whose output is a linear combination of the outputs of the given neural networks.
We conduct experiments to perform erasure coding over neural networks trained on real-world vision datasets and show that the accuracy of the decoded outputs using COIN is significantly higher than other baselines.
arXiv Detail & Related papers (2024-09-02T18:46:26Z) - A simple algorithm for output range analysis for deep neural networks [0.0]
This paper presents a novel approach for the output range estimation problem in Deep Neural Networks (DNNs) by integrating a Simulated Annealing (SA) algorithm.
The method effectively addresses the challenges by the lack of geometric information and non-linearity inherent inResNets.
arXiv Detail & Related papers (2024-07-02T22:47:40Z) - A new approach to generalisation error of machine learning algorithms:
Estimates and convergence [0.0]
We introduce a new approach to the estimation of the (generalisation) error and to convergence.
Our results include estimates of the error without any structural assumption on the neural networks.
arXiv Detail & Related papers (2023-06-23T20:57:31Z) - Guaranteed Quantization Error Computation for Neural Network Model
Compression [2.610470075814367]
Neural network model compression techniques can address the computation issue of deep neural networks on embedded devices in industrial systems.
A merged neural network is built from a feedforward neural network and its quantized version to produce the exact output difference between two neural networks.
arXiv Detail & Related papers (2023-04-26T20:21:54Z) - Intelligence Processing Units Accelerate Neuromorphic Learning [52.952192990802345]
Spiking neural networks (SNNs) have achieved orders of magnitude improvement in terms of energy consumption and latency.
We present an IPU-optimized release of our custom SNN Python package, snnTorch.
arXiv Detail & Related papers (2022-11-19T15:44:08Z) - Modeling from Features: a Mean-field Framework for Over-parameterized
Deep Neural Networks [54.27962244835622]
This paper proposes a new mean-field framework for over- parameterized deep neural networks (DNNs)
In this framework, a DNN is represented by probability measures and functions over its features in the continuous limit.
We illustrate the framework via the standard DNN and the Residual Network (Res-Net) architectures.
arXiv Detail & Related papers (2020-07-03T01:37:16Z) - Multipole Graph Neural Operator for Parametric Partial Differential
Equations [57.90284928158383]
One of the main challenges in using deep learning-based methods for simulating physical systems is formulating physics-based data.
We propose a novel multi-level graph neural network framework that captures interaction at all ranges with only linear complexity.
Experiments confirm our multi-graph network learns discretization-invariant solution operators to PDEs and can be evaluated in linear time.
arXiv Detail & Related papers (2020-06-16T21:56:22Z) - Measuring Model Complexity of Neural Networks with Curve Activation
Functions [100.98319505253797]
We propose the linear approximation neural network (LANN) to approximate a given deep model with curve activation function.
We experimentally explore the training process of neural networks and detect overfitting.
We find that the $L1$ and $L2$ regularizations suppress the increase of model complexity.
arXiv Detail & Related papers (2020-06-16T07:38:06Z) - Channel Assignment in Uplink Wireless Communication using Machine
Learning Approach [54.012791474906514]
This letter investigates a channel assignment problem in uplink wireless communication systems.
Our goal is to maximize the sum rate of all users subject to integer channel assignment constraints.
Due to high computational complexity, machine learning approaches are employed to obtain computational efficient solutions.
arXiv Detail & Related papers (2020-01-12T15:54:20Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.