Computational Complexity Evaluation of Neural Network Applications in Signal Processing

• URL: http://arxiv.org/abs/2206.12191v2
• Date: Sun, 10 Mar 2024 21:00:09 GMT
• Title: Computational Complexity Evaluation of Neural Network Applications in Signal Processing
• Authors: Pedro Freire, Sasipim Srivallapanondh, Antonio Napoli, Jaroslaw E. Prilepsky, Sergei K. Turitsyn
• Abstract summary: We provide a systematic approach for assessing and comparing the computational complexity of neural network layers in digital signal processing. One of the four metrics, called the number of additions and bit shifts ( NABS)', is newly introduced for heterogeneous quantization.
• Score: 3.4656382116457767
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this paper, we provide a systematic approach for assessing and comparing the computational complexity of neural network layers in digital signal processing. We provide and link four software-to-hardware complexity measures, defining how the different complexity metrics relate to the layers' hyper-parameters. This paper explains how to compute these four metrics for feed-forward and recurrent layers, and defines in which case we ought to use a particular metric depending on whether we characterize a more soft- or hardware-oriented application. One of the four metrics, called `the number of additions and bit shifts (NABS)', is newly introduced for heterogeneous quantization. NABS characterizes the impact of not only the bitwidth used in the operation but also the type of quantization used in the arithmetical operations. We intend this work to serve as a baseline for the different levels (purposes) of complexity estimation related to the neural networks' application in real-time digital signal processing, aiming at unifying the computational complexity estimation.

Related papers

• Efficient Learning for Linear Properties of Bounded-Gate Quantum Circuits [63.733312560668274]
  Given a quantum circuit containing d tunable RZ gates and G-d Clifford gates, can a learner perform purely classical inference to efficiently predict its linear properties? We prove that the sample complexity scaling linearly in d is necessary and sufficient to achieve a small prediction error, while the corresponding computational complexity may scale exponentially in d. We devise a kernel-based learning model capable of trading off prediction error and computational complexity, transitioning from exponential to scaling in many practical settings.
  arXiv  Detail & Related papers  (2024-08-22T08:21:28Z)
• On the Computational Complexities of Complex-valued Neural Networks [0.0]
  Complex-valued neural networks (CVNNs) are nonlinear filters used in the digital signal processing of complex-domain data. This paper presents both the quantitative and computational complexities of CVNNs.
  arXiv  Detail & Related papers  (2023-10-19T18:14:04Z)
• Incrementally-Computable Neural Networks: Efficient Inference for Dynamic Inputs [75.40636935415601]
  Deep learning often faces the challenge of efficiently processing dynamic inputs, such as sensor data or user inputs. We take an incremental computing approach, looking to reuse calculations as the inputs change. We apply this approach to the transformers architecture, creating an efficient incremental inference algorithm with complexity proportional to the fraction of modified inputs.
  arXiv  Detail & Related papers  (2023-07-27T16:30:27Z)
• Tunable Complexity Benchmarks for Evaluating Physics-Informed Neural Networks on Coupled Ordinary Differential Equations [64.78260098263489]
  In this work, we assess the ability of physics-informed neural networks (PINNs) to solve increasingly-complex coupled ordinary differential equations (ODEs) We show that PINNs eventually fail to produce correct solutions to these benchmarks as their complexity increases. We identify several reasons why this may be the case, including insufficient network capacity, poor conditioning of the ODEs, and high local curvature, as measured by the Laplacian of the PINN loss.
  arXiv  Detail & Related papers  (2022-10-14T15:01:32Z)
• Low-bit Shift Network for End-to-End Spoken Language Understanding [7.851607739211987]
  We propose the use of power-of-two quantization, which quantizes continuous parameters into low-bit power-of-two values. This reduces computational complexity by removing expensive multiplication operations and with the use of low-bit weights.
  arXiv  Detail & Related papers  (2022-07-15T14:34:22Z)
• SignalNet: A Low Resolution Sinusoid Decomposition and Estimation Network [79.04274563889548]
  We propose SignalNet, a neural network architecture that detects the number of sinusoids and estimates their parameters from quantized in-phase and quadrature samples. We introduce a worst-case learning threshold for comparing the results of our network relative to the underlying data distributions. In simulation, we find that our algorithm is always able to surpass the threshold for three-bit data but often cannot exceed the threshold for one-bit data.
  arXiv  Detail & Related papers  (2021-06-10T04:21:20Z)
• A Survey of Quantization Methods for Efficient Neural Network Inference [75.55159744950859]
  quantization is the problem of distributing continuous real-valued numbers over a fixed discrete set of numbers to minimize the number of bits required. It has come to the forefront in recent years due to the remarkable performance of Neural Network models in computer vision, natural language processing, and related areas. Moving from floating-point representations to low-precision fixed integer values represented in four bits or less holds the potential to reduce the memory footprint and latency by a factor of 16x.
  arXiv  Detail & Related papers  (2021-03-25T06:57:11Z)
• Ps and Qs: Quantization-aware pruning for efficient low latency neural network inference [56.24109486973292]
  We study the interplay between pruning and quantization during the training of neural networks for ultra low latency applications. We find that quantization-aware pruning yields more computationally efficient models than either pruning or quantization alone for our task.
  arXiv  Detail & Related papers  (2021-02-22T19:00:05Z)
• Inference with Artificial Neural Networks on Analog Neuromorphic Hardware [0.0]
  BrainScaleS-2 ASIC comprises mixed-signal neurons and synapse circuits. System can also operate in a vector-matrix multiplication and accumulation mode for artificial neural networks.
  arXiv  Detail & Related papers  (2020-06-23T17:25:06Z)
• Separation of Memory and Processing in Dual Recurrent Neural Networks [0.0]
  We explore a neural network architecture that stacks a recurrent layer and a feedforward layer that is also connected to the input. When noise is introduced into the activation function of the recurrent units, these neurons are forced into a binary activation regime that makes the networks behave much as finite automata.
  arXiv  Detail & Related papers  (2020-05-17T11:38:42Z)

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.