Efficient Real Time Recurrent Learning through combined activity and parameter sparsity

• URL: http://arxiv.org/abs/2303.05641v1
• Date: Fri, 10 Mar 2023 01:09:04 GMT
• Title: Efficient Real Time Recurrent Learning through combined activity and parameter sparsity
• Authors: Anand Subramoney
• Abstract summary: Backpropagation through time (BPTT) is the standard algorithm for training recurrent neural networks (RNNs) BPTT is unsuited for online learning and presents a challenge for implementation on low-resource real-time systems. We show that recurrent networks exhibiting high activity sparsity can reduce the computational cost of Real-Time Recurrent Learning (RTRL)
• Score: 0.5076419064097732
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Backpropagation through time (BPTT) is the standard algorithm for training recurrent neural networks (RNNs), which requires separate simulation phases for the forward and backward passes for inference and learning, respectively. Moreover, BPTT requires storing the complete history of network states between phases, with memory consumption growing proportional to the input sequence length. This makes BPTT unsuited for online learning and presents a challenge for implementation on low-resource real-time systems. Real-Time Recurrent Learning (RTRL) allows online learning, and the growth of required memory is independent of sequence length. However, RTRL suffers from exceptionally high computational costs that grow proportional to the fourth power of the state size, making RTRL computationally intractable for all but the smallest of networks. In this work, we show that recurrent networks exhibiting high activity sparsity can reduce the computational cost of RTRL. Moreover, combining activity and parameter sparsity can lead to significant enough savings in computational and memory costs to make RTRL practical. Unlike previous work, this improvement in the efficiency of RTRL can be achieved without using any approximations for the learning process.

Related papers

• Real-Time Recurrent Reinforcement Learning [7.737685867200335]
  RTRRL consists of three parts: (1) a Meta-RL RNN architecture, implementing on its own an actor-critic algorithm; (2) an outer reinforcement learning algorithm, exploiting temporal difference learning and dutch eligibility traces to train the Meta-RL network; and (3) random-feedback local-online (RFLO) learning, an online automatic differentiation algorithm for computing the gradients with respect to parameters of the network.
  arXiv  Detail & Related papers  (2023-11-08T16:56:16Z)
• S-TLLR: STDP-inspired Temporal Local Learning Rule for Spiking Neural Networks [7.573297026523597]
  Spiking Neural Networks (SNNs) are biologically plausible models that have been identified as potentially apt for deploying energy-efficient intelligence at the edge. We propose S-TLLR, a novel three-factor temporal local learning rule inspired by the Spike-Timing Dependent Plasticity (STDP) mechanism. S-TLLR is designed to have low memory and time complexities, which are independent of the number of time steps, rendering it suitable for online learning on low-power edge devices.
  arXiv  Detail & Related papers  (2023-06-27T05:44:56Z)
• Towards Memory- and Time-Efficient Backpropagation for Training Spiking Neural Networks [70.75043144299168]
  Spiking Neural Networks (SNNs) are promising energy-efficient models for neuromorphic computing. We propose the Spatial Learning Through Time (SLTT) method that can achieve high performance while greatly improving training efficiency. Our method achieves state-of-the-art accuracy on ImageNet, while the memory cost and training time are reduced by more than 70% and 50%, respectively, compared with BPTT.
  arXiv  Detail & Related papers  (2023-02-28T05:01:01Z)
• Scalable Real-Time Recurrent Learning Using Columnar-Constructive Networks [19.248060562241296]
  We propose two constraints that make real-time recurrent learning scalable. We show that by either decomposing the network into independent modules or learning the network in stages, we can make RTRL scale linearly with the number of parameters. We demonstrate the effectiveness of our approach over Truncated-BPTT on a prediction benchmark inspired by animal learning and by doing policy evaluation of pre-trained policies for Atari 2600 games.
  arXiv  Detail & Related papers  (2023-01-20T23:17:48Z)
• Intelligence Processing Units Accelerate Neuromorphic Learning [52.952192990802345]
  Spiking neural networks (SNNs) have achieved orders of magnitude improvement in terms of energy consumption and latency. We present an IPU-optimized release of our custom SNN Python package, snnTorch.
  arXiv  Detail & Related papers  (2022-11-19T15:44:08Z)
• Online Training Through Time for Spiking Neural Networks [66.7744060103562]
  Spiking neural networks (SNNs) are promising brain-inspired energy-efficient models. Recent progress in training methods has enabled successful deep SNNs on large-scale tasks with low latency. We propose online training through time (OTTT) for SNNs, which is derived from BPTT to enable forward-in-time learning.
  arXiv  Detail & Related papers  (2022-10-09T07:47:56Z)
• Single-Shot Pruning for Offline Reinforcement Learning [47.886329599997474]
  Deep Reinforcement Learning (RL) is a powerful framework for solving complex real-world problems. One way to tackle this problem is to prune neural networks leaving only the necessary parameters. We close the gap between RL and single-shot pruning techniques and present a general pruning approach to the Offline RL.
  arXiv  Detail & Related papers  (2021-12-31T18:10:02Z)
• Boosting the Convergence of Reinforcement Learning-based Auto-pruning Using Historical Data [35.36703623383735]
  Reinforcement learning (RL)-based auto-pruning has been proposed to automate the pruning process to avoid expensive hand-crafted work. However, the RL-based pruner involves a time-consuming training process and the high expense of each sample further exacerbates this problem. We propose an efficient auto-pruning framework which solves this problem by taking advantage of the historical data from the previous auto-pruning process.
  arXiv  Detail & Related papers  (2021-07-16T07:17:26Z)
• Online learning of windmill time series using Long Short-term Cognitive Networks [58.675240242609064]
  The amount of data generated on windmill farms makes online learning the most viable strategy to follow. We use Long Short-term Cognitive Networks (LSTCNs) to forecast windmill time series in online settings. Our approach reported the lowest forecasting errors with respect to a simple RNN, a Long Short-term Memory, a Gated Recurrent Unit, and a Hidden Markov Model.
  arXiv  Detail & Related papers  (2021-07-01T13:13:24Z)
• Improving Computational Efficiency in Visual Reinforcement Learning via Stored Embeddings [89.63764845984076]
  We present Stored Embeddings for Efficient Reinforcement Learning (SEER) SEER is a simple modification of existing off-policy deep reinforcement learning methods. We show that SEER does not degrade the performance of RLizable agents while significantly saving computation and memory.
  arXiv  Detail & Related papers  (2021-03-04T08:14:10Z)
• A Practical Sparse Approximation for Real Time Recurrent Learning [38.19296522866088]
  Real Time Recurrent Learning (RTRL) eliminates the need for history storage and allows for online weight updates. We introduce the Sparse n-step Approximation (SnAp) to the RTRL influence matrix, which only keeps entries that are nonzero within n steps of the recurrent core. For highly sparse networks, SnAp with n=2 remains tractable and can outperform backpropagation through time in terms of learning speed when updates are done online.
  arXiv  Detail & Related papers  (2020-06-12T14:38:15Z)

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.