Dynamic Precision Analog Computing for Neural Networks

• URL: http://arxiv.org/abs/2102.06365v1
• Date: Fri, 12 Feb 2021 06:56:56 GMT
• Title: Dynamic Precision Analog Computing for Neural Networks
• Abstract summary: We propose extending analog computing architectures to support varying levels of precision by repeating operations and averaging the result. We find that employing dynamic precision reduces energy consumption by up to 89% for computer vision models such as Resnet50 and by 24% for natural language processing models such as BERT.
• Score: 0.7701333337093469
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Analog electronic and optical computing exhibit tremendous advantages over digital computing for accelerating deep learning when operations are executed at low precision. In this work, we derive a relationship between analog precision, which is limited by noise, and digital bit precision. We propose extending analog computing architectures to support varying levels of precision by repeating operations and averaging the result, decreasing the impact of noise. Such architectures enable programmable tradeoffs between precision and other desirable performance metrics such as energy efficiency or throughput. To utilize dynamic precision, we propose a method for learning the precision of each layer of a pre-trained model without retraining network weights. We evaluate this method on analog architectures subject to a variety of noise sources such as shot noise, thermal noise, and weight noise and find that employing dynamic precision reduces energy consumption by up to 89% for computer vision models such as Resnet50 and by 24% for natural language processing models such as BERT. In one example, we apply dynamic precision to a shot-noise limited homodyne optical neural network and simulate inference at an optical energy consumption of 2.7 aJ/MAC for Resnet50 and 1.6 aJ/MAC for BERT with <2% accuracy degradation.

Related papers

• ThRIve: Thermally Robust CNN Inference via Low-Rank Adaptation in Heterogeneous PIM Architectures [13.754183593794131]
  Processing-In-Memory (PIM) has emerged as a promising technology for accelerating machine learning (ML) workloads.<n>PIM devices suffer from non-idealities such as thermal noise.<n>This noise alters the stored values in the memory cells which correspond to actual model weights, compromising the inference accuracy.<n>We introduce ThRIve, a noise-aware training methodology that leverages low-rank adaptation to enable thermally robust inference.
  arXiv  Detail & Related papers  (2026-07-19T06:03:25Z)
• Extending Straight-Through Estimation for Robust Neural Networks on Analog CIM Hardware [5.100973962435092]
  We propose a noise-aware training method for analog Compute-In-Memory (CIM) systems.<n>We decouple forward noise simulation from backward gradient computation, enabling noise-aware training with more accurate but computationally intractable noise modeling.<n>Our framework achieves up to 5.3% accuracy improvement on image classification, 0.72 perplexity reduction on text generation, 2.2$times$ speedup in training time, and 37.9% lower peak memory usage.
  arXiv  Detail & Related papers  (2025-08-16T06:53:44Z)
• Towards a Digital Twin of Noisy Quantum Computers: Calibration-Driven Emulation of Transmon Qubits [0.0]
  We develop a digital twin of a superconducting transmon qubit device. The model parameters are extracted from hardware calibration data. We validate our model by comparing its predictions with experimental results from a 5-qubit QPU.
  arXiv  Detail & Related papers  (2025-04-11T07:30:53Z)
• Efficient Noise Mitigation for Enhancing Inference Accuracy in DNNs on Mixed-Signal Accelerators [4.416800723562206]
  We model process-induced and aging-related variations of analog computing components on the accuracy of the analog neural networks. We introduce a denoising block inserted between selected layers of a pre-trained model. We demonstrate that training the denoising block significantly increases the model's robustness against various noise levels.
  arXiv  Detail & Related papers  (2024-09-27T08:45:55Z)
• On-Chip Learning with Memristor-Based Neural Networks: Assessing Accuracy and Efficiency Under Device Variations, Conductance Errors, and Input Noise [0.0]
  This paper presents a memristor-based compute-in-memory hardware accelerator for on-chip training and inference. Hardware, consisting of 30 memristors and 4 neurons, utilizes three different M-SDC structures with tungsten, chromium, and carbon media to perform binary image classification tasks.
  arXiv  Detail & Related papers  (2024-08-26T23:10:01Z)
• Pruning random resistive memory for optimizing analogue AI [54.21621702814583]
  AI models present unprecedented challenges to energy consumption and environmental sustainability. One promising solution is to revisit analogue computing, a technique that predates digital computing. Here, we report a universal solution, software-hardware co-design using structural plasticity-inspired edge pruning.
  arXiv  Detail & Related papers  (2023-11-13T08:59:01Z)
• 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)
• Quantized Neural Networks for Low-Precision Accumulation with Guaranteed Overflow Avoidance [68.8204255655161]
  We introduce a quantization-aware training algorithm that guarantees avoiding numerical overflow when reducing the precision of accumulators during inference. We evaluate our algorithm across multiple quantized models that we train for different tasks, showing that our approach can reduce the precision of accumulators while maintaining model accuracy with respect to a floating-point baseline.
  arXiv  Detail & Related papers  (2023-01-31T02:46:57Z)
• Walking Noise: On Layer-Specific Robustness of Neural Architectures against Noisy Computations and Associated Characteristic Learning Dynamics [1.5184189132709105]
  We discuss the implications of additive, multiplicative and mixed noise for different classification tasks and model architectures. We propose a methodology called Walking Noise which injects layer-specific noise to measure the robustness. We conclude with a discussion of the use of this methodology in practice, among others, discussing its use for tailored multi-execution in noisy environments.
  arXiv  Detail & Related papers  (2022-12-20T17:09:08Z)
• Single-Shot Optical Neural Network [55.41644538483948]
  'Weight-stationary' analog optical and electronic hardware has been proposed to reduce the compute resources required by deep neural networks. We present a scalable, single-shot-per-layer weight-stationary optical processor.
  arXiv  Detail & Related papers  (2022-05-18T17:49:49Z)
• Mixed Precision Low-bit Quantization of Neural Network Language Models for Speech Recognition [67.95996816744251]
  State-of-the-art language models (LMs) represented by long-short term memory recurrent neural networks (LSTM-RNNs) and Transformers are becoming increasingly complex and expensive for practical applications. Current quantization methods are based on uniform precision and fail to account for the varying performance sensitivity at different parts of LMs to quantization errors. Novel mixed precision neural network LM quantization methods are proposed in this paper.
  arXiv  Detail & Related papers  (2021-11-29T12:24:02Z)
• Mixed Precision of Quantization of Transformer Language Models for Speech Recognition [67.95996816744251]
  State-of-the-art neural language models represented by Transformers are becoming increasingly complex and expensive for practical applications. Current low-bit quantization methods are based on uniform precision and fail to account for the varying performance sensitivity at different parts of the system to quantization errors. The optimal local precision settings are automatically learned using two techniques. Experiments conducted on Penn Treebank (PTB) and a Switchboard corpus trained LF-MMI TDNN system.
  arXiv  Detail & Related papers  (2021-11-29T09:57:00Z)
• Training of mixed-signal optical convolutional neural network with reduced quantization level [1.3381749415517021]
  Mixed-signal artificial neural networks (ANNs) that employ analog matrix-multiplication accelerators can achieve higher speed and improved power efficiency. Here we report a training method for mixed-signal ANN with two types of errors in its analog signals, random noise, and deterministic errors (distortions) The results showed that mixed-signal ANNs trained with our proposed method can achieve an equivalent classification accuracy with noise level up to 50% of the ideal quantization step size.
  arXiv  Detail & Related papers  (2020-08-20T20:46:22Z)
• Robust Processing-In-Memory Neural Networks via Noise-Aware Normalization [26.270754571140735]
  PIM accelerators often suffer from intrinsic noise in the physical components. We propose a noise-agnostic method to achieve robust neural network performance against any noise setting.
  arXiv  Detail & Related papers  (2020-07-07T06:51:28Z)

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.