Learning-to-learn enables rapid learning with phase-change memory-based in-memory computing

• URL: http://arxiv.org/abs/2405.05141v1
• Date: Mon, 22 Apr 2024 15:03:46 GMT
• Title: Learning-to-learn enables rapid learning with phase-change memory-based in-memory computing
• Authors: Thomas Ortner, Horst Petschenig, Athanasios Vasilopoulos, Roland Renner, Špela Brglez, Thomas Limbacher, Enrique Piñero, Alejandro Linares Barranco, Angeliki Pantazi, Robert Legenstein,
• Abstract summary: A growing demand for low-power, autonomously learning artificial intelligence (AI) systems can be applied at the edge and rapidly adapt to the specific situation at deployment site. In this work, we pair L2L with in-memory computing neuromorphic hardware to build efficient AI models that can rapidly adapt to new tasks. We demonstrate the versatility of our approach in two scenarios: a convolutional neural network performing image classification and a biologically-inspired spiking neural network generating motor commands for a real robotic arm.
• Score: 38.34244217803562
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: There is a growing demand for low-power, autonomously learning artificial intelligence (AI) systems that can be applied at the edge and rapidly adapt to the specific situation at deployment site. However, current AI models struggle in such scenarios, often requiring extensive fine-tuning, computational resources, and data. In contrast, humans can effortlessly adjust to new tasks by transferring knowledge from related ones. The concept of learning-to-learn (L2L) mimics this process and enables AI models to rapidly adapt with only little computational effort and data. In-memory computing neuromorphic hardware (NMHW) is inspired by the brain's operating principles and mimics its physical co-location of memory and compute. In this work, we pair L2L with in-memory computing NMHW based on phase-change memory devices to build efficient AI models that can rapidly adapt to new tasks. We demonstrate the versatility of our approach in two scenarios: a convolutional neural network performing image classification and a biologically-inspired spiking neural network generating motor commands for a real robotic arm. Both models rapidly learn with few parameter updates. Deployed on the NMHW, they perform on-par with their software equivalents. Moreover, meta-training of these models can be performed in software with high-precision, alleviating the need for accurate hardware models.

Related papers

• Emulating Brain-like Rapid Learning in Neuromorphic Edge Computing [3.735012564657653]
  Digital neuromorphic technology simulates the neural and synaptic processes of the brain using two stages of learning. We demonstrate our approach using event-driven vision sensor data and the Intel Loihi neuromorphic processor with its plasticity dynamics. Our methodology can be deployed with arbitrary plasticity models and can be applied to situations demanding quick learning and adaptation at the edge.
  arXiv  Detail & Related papers  (2024-08-28T13:51:52Z)
• GreenLightningAI: An Efficient AI System with Decoupled Structural and Quantitative Knowledge [0.0]
  Training powerful and popular deep neural networks comes at very high economic and environmental costs. This work takes a radically different approach by proposing GreenLightningAI. The new AI system stores the information required to select the system subset for a given sample. We show experimentally that the structural information can be kept unmodified when re-training the AI system with new samples.
  arXiv  Detail & Related papers  (2023-12-15T17:34:11Z)
• Brain-Inspired Computational Intelligence via Predictive Coding [89.6335791546526]
  Predictive coding (PC) has shown promising performance in machine intelligence tasks. PC can model information processing in different brain areas, can be used in cognitive control and robotics.
  arXiv  Detail & Related papers  (2023-08-15T16:37:16Z)
• Meta-Learning in Spiking Neural Networks with Reward-Modulated STDP [2.179313476241343]
  We propose a bio-plausible meta-learning model inspired by the hippocampus and the prefrontal cortex. Our new model can easily be applied to spike-based neuromorphic devices and enables fast learning in neuromorphic hardware.
  arXiv  Detail & Related papers  (2023-06-07T13:08:46Z)
• Hindsight States: Blending Sim and Real Task Elements for Efficient Reinforcement Learning [61.3506230781327]
  In robotics, one approach to generate training data builds on simulations based on dynamics models derived from first principles. Here, we leverage the imbalance in complexity of the dynamics to learn more sample-efficiently. We validate our method on several challenging simulated tasks and demonstrate that it improves learning both alone and when combined with an existing hindsight algorithm.
  arXiv  Detail & Related papers  (2023-03-03T21:55:04Z)
• Incremental Online Learning Algorithms Comparison for Gesture and Visual Smart Sensors [68.8204255655161]
  This paper compares four state-of-the-art algorithms in two real applications: gesture recognition based on accelerometer data and image classification. Our results confirm these systems' reliability and the feasibility of deploying them in tiny-memory MCUs.
  arXiv  Detail & Related papers  (2022-09-01T17:05:20Z)
• Reservoir Memory Machines as Neural Computers [70.5993855765376]
  Differentiable neural computers extend artificial neural networks with an explicit memory without interference. We achieve some of the computational capabilities of differentiable neural computers with a model that can be trained very efficiently.
  arXiv  Detail & Related papers  (2020-09-14T12:01:30Z)
• 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)
• 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)
• Integration of Leaky-Integrate-and-Fire-Neurons in Deep Learning Architectures [0.0]
  We show that biologically inspired neuron models provide novel and efficient ways of information encoding. We derived simple update-rules for the LIF units from the differential equations, which are easy to numerically integrate. We apply our method to the IRIS blossoms image data set and show that the training technique can be used to train LIF neurons on image classification tasks.
  arXiv  Detail & Related papers  (2020-04-28T13:57:42Z)

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.