Analog Alchemy: Neural Computation with In-Memory Inference, Learning and Routing

• URL: http://arxiv.org/abs/2412.20848v1
• Date: Mon, 30 Dec 2024 10:35:03 GMT
• Title: Analog Alchemy: Neural Computation with In-Memory Inference, Learning and Routing
• Authors: Yigit Demirag,
• Abstract summary: I explore an alternative way with memristive devices for neural computation, where the unique physical dynamics of the devices are used for inference, learning and routing. I will provide hardware evidence of adaptability of local learning to memristive substrates, new material stacks and circuit blocks that aid in solving the credit assignment problem and efficient routing between analog crossbars for scalable architectures.
• Score: 0.08965418284317034
• License:
• Abstract: As neural computation is revolutionizing the field of Artificial Intelligence (AI), rethinking the ideal neural hardware is becoming the next frontier. Fast and reliable von Neumann architecture has been the hosting platform for neural computation. Although capable, its separation of memory and computation creates the bottleneck for the energy efficiency of neural computation, contrasting the biological brain. The question remains: how can we efficiently combine memory and computation, while exploiting the physics of the substrate, to build intelligent systems? In this thesis, I explore an alternative way with memristive devices for neural computation, where the unique physical dynamics of the devices are used for inference, learning and routing. Guided by the principles of gradient-based learning, we selected functions that need to be materialized, and analyzed connectomics principles for efficient wiring. Despite non-idealities and noise inherent in analog physics, I will provide hardware evidence of adaptability of local learning to memristive substrates, new material stacks and circuit blocks that aid in solving the credit assignment problem and efficient routing between analog crossbars for scalable architectures.

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)
• 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)
• Biologically Plausible Learning on Neuromorphic Hardware Architectures [27.138481022472]
  Neuromorphic computing is an emerging paradigm that confronts this imbalance by computations directly in analog memories. This work is the first to compare the impact of different learning algorithms on Compute-In-Memory-based hardware and vice versa.
  arXiv  Detail & Related papers  (2022-12-29T15:10:59Z)
• Neuromorphic Artificial Intelligence Systems [58.1806704582023]
  Modern AI systems, based on von Neumann architecture and classical neural networks, have a number of fundamental limitations in comparison with the brain. This article discusses such limitations and the ways they can be mitigated. It presents an overview of currently available neuromorphic AI projects in which these limitations are overcome.
  arXiv  Detail & Related papers  (2022-05-25T20:16:05Z)
• A Robust Learning Rule for Soft-Bounded Memristive Synapses Competitive with Supervised Learning in Standard Spiking Neural Networks [0.0]
  A view in theoretical neuroscience sees the brain as a function-computing device. Being able to approximate functions is a fundamental axiom to build upon for future brain research. In this work we apply a novel supervised learning algorithm - based on controlling niobium-doped strontium titanate memristive synapses - to learning non-trivial multidimensional functions.
  arXiv  Detail & Related papers  (2022-04-12T10:21:22Z)
• Mapping and Validating a Point Neuron Model on Intel's Neuromorphic Hardware Loihi [77.34726150561087]
  We investigate the potential of Intel's fifth generation neuromorphic chip - Loihi' Loihi is based on the novel idea of Spiking Neural Networks (SNNs) emulating the neurons in the brain. We find that Loihi replicates classical simulations very efficiently and scales notably well in terms of both time and energy performance as the networks get larger.
  arXiv  Detail & Related papers  (2021-09-22T16:52:51Z)
• A deep learning theory for neural networks grounded in physics [2.132096006921048]
  We argue that building large, fast and efficient neural networks on neuromorphic architectures requires rethinking the algorithms to implement and train them. Our framework applies to a very broad class of models, namely systems whose state or dynamics are described by variational equations.
  arXiv  Detail & Related papers  (2021-03-18T02:12:48Z)
• One-step regression and classification with crosspoint resistive memory arrays [62.997667081978825]
  High speed, low energy computing machines are in demand to enable real-time artificial intelligence at the edge. One-step learning is supported by simulations of the prediction of the cost of a house in Boston and the training of a 2-layer neural network for MNIST digit recognition. Results are all obtained in one computational step, thanks to the physical, parallel, and analog computing within the crosspoint array.
  arXiv  Detail & Related papers  (2020-05-05T08:00:07Z)
• 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)
• Memristors -- from In-memory computing, Deep Learning Acceleration, Spiking Neural Networks, to the Future of Neuromorphic and Bio-inspired Computing [25.16076541420544]
  Machine learning, particularly in the form of deep learning, has driven most of the recent fundamental developments in artificial intelligence. Deep learning has been successfully applied in areas such as object/pattern recognition, speech and natural language processing, self-driving vehicles, intelligent self-diagnostics tools, autonomous robots, knowledgeable personal assistants, and monitoring. This paper reviews the case for a novel beyond CMOS hardware technology, memristors, as a potential solution for the implementation of power-efficient in-memory computing, deep learning accelerators, and spiking neural networks.
  arXiv  Detail & Related papers  (2020-04-30T16:49:03Z)

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.