Efficient Representation of the Activation Space in Deep Neural Networks

• URL: http://arxiv.org/abs/2312.08143v1
• Date: Wed, 13 Dec 2023 13:46:14 GMT
• Title: Efficient Representation of the Activation Space in Deep Neural Networks
• Authors: Tanya Akumu, Celia Cintas, Girmaw Abebe Tadesse, Adebayo Oshingbesan, Skyler Speakman, Edward McFowland III
• Abstract summary: We propose a model-agnostic framework for creating representations of activations in deep neural networks. The framework reduces memory usage by 30% with up to 4 times faster p-value computing time. As we do not persist raw data at inference time, we could potentially reduce susceptibility to attacks and privacy issues.
• Score: 5.224743522146324
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The representations of the activation space of deep neural networks (DNNs) are widely utilized for tasks like natural language processing, anomaly detection and speech recognition. Due to the diverse nature of these tasks and the large size of DNNs, an efficient and task-independent representation of activations becomes crucial. Empirical p-values have been used to quantify the relative strength of an observed node activation compared to activations created by already-known inputs. Nonetheless, keeping raw data for these calculations increases memory resource consumption and raises privacy concerns. To this end, we propose a model-agnostic framework for creating representations of activations in DNNs using node-specific histograms to compute p-values of observed activations without retaining already-known inputs. Our proposed approach demonstrates promising potential when validated with multiple network architectures across various downstream tasks and compared with the kernel density estimates and brute-force empirical baselines. In addition, the framework reduces memory usage by 30% with up to 4 times faster p-value computing time while maintaining state of-the-art detection power in downstream tasks such as the detection of adversarial attacks and synthesized content. Moreover, as we do not persist raw data at inference time, we could potentially reduce susceptibility to attacks and privacy issues.

Related papers

• Heterogenous Memory Augmented Neural Networks [84.29338268789684]
  We introduce a novel heterogeneous memory augmentation approach for neural networks. By introducing learnable memory tokens with attention mechanism, we can effectively boost performance without huge computational overhead. We show our approach on various image and graph-based tasks under both in-distribution (ID) and out-of-distribution (OOD) conditions.
  arXiv  Detail & Related papers  (2023-10-17T01:05:28Z)
• A Geometrical Approach to Evaluate the Adversarial Robustness of Deep Neural Networks [52.09243852066406]
  Adversarial Converging Time Score (ACTS) measures the converging time as an adversarial robustness metric. We validate the effectiveness and generalization of the proposed ACTS metric against different adversarial attacks on the large-scale ImageNet dataset.
  arXiv  Detail & Related papers  (2023-10-10T09:39:38Z)
• Spiking Neural Networks for event-based action recognition: A new task to understand their advantage [1.4348901037145936]
  Spiking Neural Networks (SNNs) are characterised by their unique temporal dynamics. We show how Spiking neurons can enable temporal feature extraction in feed-forward neural networks. We also show how recurrent SNNs can achieve comparable results to LSTM with a smaller number of parameters.
  arXiv  Detail & Related papers  (2022-09-29T16:22:46Z)
• Braille Letter Reading: A Benchmark for Spatio-Temporal Pattern Recognition on Neuromorphic Hardware [50.380319968947035]
  Recent deep learning approaches have reached accuracy in such tasks, but their implementation on conventional embedded solutions is still computationally very and energy expensive. We propose a new benchmark for computing tactile pattern recognition at the edge through letters reading. We trained and compared feed-forward and recurrent spiking neural networks (SNNs) offline using back-propagation through time with surrogate gradients, then we deployed them on the Intel Loihimorphic chip for efficient inference. Our results show that the LSTM outperforms the recurrent SNN in terms of accuracy by 14%. However, the recurrent SNN on Loihi is 237 times more energy
  arXiv  Detail & Related papers  (2022-05-30T14:30:45Z)
• Abstraction and Symbolic Execution of Deep Neural Networks with Bayesian Approximation of Hidden Features [8.723426955657345]
  We propose a novel abstraction method which abstracts a deep neural network and a dataset into a Bayesian network. We make use of dimensionality reduction techniques to identify hidden features that have been learned by hidden layers of the DNN. We can derive a runtime monitoring approach to detect in operational time rare inputs.
  arXiv  Detail & Related papers  (2021-03-05T14:28:42Z)
• Deep ConvLSTM with self-attention for human activity decoding using wearables [0.0]
  We propose a deep neural network architecture that captures features of multiple sensor time-series data but also selects important time points. We show the validity of the proposed approach across different data sampling strategies and demonstrate that the self-attention mechanism gave a significant improvement. The proposed methods open avenues for better decoding of human activity from multiple body sensors over extended periods time.
  arXiv  Detail & Related papers  (2020-05-02T04:30:31Z)
• Rectified Linear Postsynaptic Potential Function for Backpropagation in Deep Spiking Neural Networks [55.0627904986664]
  Spiking Neural Networks (SNNs) usetemporal spike patterns to represent and transmit information, which is not only biologically realistic but also suitable for ultra-low-power event-driven neuromorphic implementation. This paper investigates the contribution of spike timing dynamics to information encoding, synaptic plasticity and decision making, providing a new perspective to design of future DeepSNNs and neuromorphic hardware systems.
  arXiv  Detail & Related papers  (2020-03-26T11:13:07Z)
• Depth Enables Long-Term Memory for Recurrent Neural Networks [0.0]
  We introduce a measure of the network's ability to support information flow across time, referred to as the Start-End separation rank. We prove that deep recurrent networks support Start-End separation ranks which are higher than those supported by their shallow counterparts.
  arXiv  Detail & Related papers  (2020-03-23T10:29:14Z)
• BiDet: An Efficient Binarized Object Detector [96.19708396510894]
  We propose a binarized neural network learning method called BiDet for efficient object detection. Our BiDet fully utilizes the representational capacity of the binary neural networks for object detection by redundancy removal. Our method outperforms the state-of-the-art binary neural networks by a sizable margin.
  arXiv  Detail & Related papers  (2020-03-09T08:16:16Z)
• Temporal Pulses Driven Spiking Neural Network for Fast Object Recognition in Autonomous Driving [65.36115045035903]
  We propose an approach to address the object recognition problem directly with raw temporal pulses utilizing the spiking neural network (SNN) Being evaluated on various datasets, our proposed method has shown comparable performance as the state-of-the-art methods, while achieving remarkable time efficiency.
  arXiv  Detail & Related papers  (2020-01-24T22:58:55Z)

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.