In-memory factorization of holographic perceptual representations

• URL: http://arxiv.org/abs/2211.05052v1
• Date: Wed, 9 Nov 2022 17:36:06 GMT
• Title: In-memory factorization of holographic perceptual representations
• Authors: Jovin Langenegger, Geethan Karunaratne, Michael Hersche, Luca Benini, Abu Sebastian, Abbas Rahimi
• Abstract summary: Disentanglement of constituent factors of a sensory signal is central to perception and cognition. We present a compute engine capable of efficiently factorizing holographic perceptual representations.
• Score: 14.621617156897301
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Disentanglement of constituent factors of a sensory signal is central to perception and cognition and hence is a critical task for future artificial intelligence systems. In this paper, we present a compute engine capable of efficiently factorizing holographic perceptual representations by exploiting the computation-in-superposition capability of brain-inspired hyperdimensional computing and the intrinsic stochasticity associated with analog in-memory computing based on nanoscale memristive devices. Such an iterative in-memory factorizer is shown to solve at least five orders of magnitude larger problems that cannot be solved otherwise, while also significantly lowering the computational time and space complexity. We present a large-scale experimental demonstration of the factorizer by employing two in-memory compute chips based on phase-change memristive devices. The dominant matrix-vector multiply operations are executed at O(1) thus reducing the computational time complexity to merely the number of iterations. Moreover, we experimentally demonstrate the ability to factorize visual perceptual representations reliably and efficiently.

Related papers

• Resistive Memory-based Neural Differential Equation Solver for Score-based Diffusion Model [55.116403765330084]
  Current AIGC methods, such as score-based diffusion, are still deficient in terms of rapidity and efficiency. We propose a time-continuous and analog in-memory neural differential equation solver for score-based diffusion. We experimentally validate our solution with 180 nm resistive memory in-memory computing macros.
  arXiv  Detail & Related papers  (2024-04-08T16:34:35Z)
• H3DFact: Heterogeneous 3D Integrated CIM for Factorization with Holographic Perceptual Representations [6.3347476400923615]
  H3DFact is a heterogeneous 3D integrated in-memory compute engine capable of efficiently factorizing high-dimensional holographic representations. H3DFact exploits the computation-in-superposition capability of holographic vectors and the intrinsicity associated with memristive-based 3D compute-in-memory.
  arXiv  Detail & Related papers  (2024-04-05T15:32:49Z)
• Randomized Dimension Reduction with Statistical Guarantees [0.27195102129095]
  This thesis explores some of such algorithms for fast execution and efficient data utilization. We focus on learning algorithms with various incorporations of data augmentation that improve generalization and distributional provably. Specifically, Chapter 4 presents a sample complexity analysis for data augmentation consistency regularization.
  arXiv  Detail & Related papers  (2023-10-03T02:01:39Z)
• Randomized Polar Codes for Anytime Distributed Machine Learning [66.46612460837147]
  We present a novel distributed computing framework that is robust to slow compute nodes, and is capable of both approximate and exact computation of linear operations. We propose a sequential decoding algorithm designed to handle real valued data while maintaining low computational complexity for recovery. We demonstrate the potential applications of this framework in various contexts, such as large-scale matrix multiplication and black-box optimization.
  arXiv  Detail & Related papers  (2023-09-01T18:02:04Z)
• Towards Model-Size Agnostic, Compute-Free, Memorization-based Inference of Deep Learning [5.41530201129053]
  This paper proposes a novel memorization-based inference (MBI) that is compute free and only requires lookups. Specifically, our work capitalizes on the inference mechanism of the recurrent attention model (RAM) By leveraging the low-dimensionality of glimpse, our inference procedure stores key value pairs comprising of glimpse location, patch vector, etc. in a table. The computations are obviated during inference by utilizing the table to read out key-value pairs and performing compute-free inference by memorization.
  arXiv  Detail & Related papers  (2023-07-14T21:01:59Z)
• Determinantal Point Process Attention Over Grid Cell Code Supports Out of Distribution Generalization [5.422292504420425]
  We identify properties of processing in the brain that may contribute to strong generalization performance. We show that a loss function that combines standard task-optimized error with DPP-A can exploit the recurring motifs in the grid cell code. This provides both an interpretation of how the grid cell code in the mammalian brain may contribute to generalization performance.
  arXiv  Detail & Related papers  (2023-05-28T19:07:55Z)
• Linear Self-Attention Approximation via Trainable Feedforward Kernel [77.34726150561087]
  In pursuit of faster computation, Efficient Transformers demonstrate an impressive variety of approaches. We aim to expand the idea of trainable kernel methods to approximate the self-attention mechanism of the Transformer architecture.
  arXiv  Detail & Related papers  (2022-11-08T08:14:11Z)
• Bioinspired Cortex-based Fast Codebook Generation [0.09449650062296822]
  We introduce a feature extraction method inspired by sensory cortical networks in the brain. Dubbed as bioinspired cortex, the algorithm provides convergence to features from streaming signals with superior computational efficiency. We show herein the superior performance of the cortex model in clustering and vector quantization.
  arXiv  Detail & Related papers  (2022-01-28T18:37:43Z)
• Mitigating Performance Saturation in Neural Marked Point Processes: Architectures and Loss Functions [50.674773358075015]
  We propose a simple graph-based network structure called GCHP, which utilizes only graph convolutional layers. We show that GCHP can significantly reduce training time and the likelihood ratio loss with interarrival time probability assumptions can greatly improve the model performance.
  arXiv  Detail & Related papers  (2021-07-07T16:59:14Z)
• Post-Training Quantization for Vision Transformer [85.57953732941101]
  We present an effective post-training quantization algorithm for reducing the memory storage and computational costs of vision transformers. We can obtain an 81.29% top-1 accuracy using DeiT-B model on ImageNet dataset with about 8-bit quantization.
  arXiv  Detail & Related papers  (2021-06-27T06:27:22Z)
• Spiking Neural Networks Hardware Implementations and Challenges: a Survey [53.429871539789445]
  Spiking Neural Networks are cognitive algorithms mimicking neuron and synapse operational principles. We present the state of the art of hardware implementations of spiking neural networks. We discuss the strategies employed to leverage the characteristics of these event-driven algorithms at the hardware level.
  arXiv  Detail & Related papers  (2020-05-04T13:24:00Z)

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.