Training Physical Neural Networks for Analog In-Memory Computing
- URL: http://arxiv.org/abs/2412.09010v1
- Date: Thu, 12 Dec 2024 07:22:23 GMT
- Title: Training Physical Neural Networks for Analog In-Memory Computing
- Authors: Yusuke Sakemi, Yuji Okamoto, Takashi Morie, Sou Nobukawa, Takeo Hosomi, Kazuyuki Aihara,
- Abstract summary: This paper presents physical neural networks (PNNs) for constructing physical models of IMC.
We show that hardware non-idealities traditionally viewed as detrimental can enhance the model's learning performance.
- Score: 5.582327246405357
- License:
- Abstract: In-memory computing (IMC) architectures mitigate the von Neumann bottleneck encountered in traditional deep learning accelerators. Its energy efficiency can realize deep learning-based edge applications. However, because IMC is implemented using analog circuits, inherent non-idealities in the hardware pose significant challenges. This paper presents physical neural networks (PNNs) for constructing physical models of IMC. PNNs can address the synaptic current's dependence on membrane potential, a challenge in charge-domain IMC systems. The proposed model is mathematically equivalent to spiking neural networks with reversal potentials. With a novel technique called differentiable spike-time discretization, the PNNs are efficiently trained. We show that hardware non-idealities traditionally viewed as detrimental can enhance the model's learning performance. This bottom-up methodology was validated by designing an IMC circuit with non-ideal characteristics using the sky130 process. When employing this bottom-up approach, the modeling error reduced by an order of magnitude compared to conventional top-down methods in post-layout simulations.
Related papers
- Comprehensive Online Training and Deployment for Spiking Neural Networks [40.255762156745405]
Spiking Neural Networks (SNNs) are considered to have enormous potential in the future development of Artificial Intelligence (AI)
The current proposed online training methods cannot tackle the inseparability problem of temporal dependent gradients.
We propose Efficient Multi-Precision Firing (EM-PF) model, which is a family of advanced spiking models based on floating-point spikes and binary synaptic weights.
arXiv Detail & Related papers (2024-10-10T02:39:22Z) - Scalable Mechanistic Neural Networks [52.28945097811129]
We propose an enhanced neural network framework designed for scientific machine learning applications involving long temporal sequences.
By reformulating the original Mechanistic Neural Network (MNN) we reduce the computational time and space complexities from cubic and quadratic with respect to the sequence length, respectively, to linear.
Extensive experiments demonstrate that S-MNN matches the original MNN in precision while substantially reducing computational resources.
arXiv Detail & Related papers (2024-10-08T14:27:28Z) - Physics-Informed Neural Networks with Hard Linear Equality Constraints [9.101849365688905]
This work proposes a novel physics-informed neural network, KKT-hPINN, which rigorously guarantees hard linear equality constraints.
Experiments on Aspen models of a stirred-tank reactor unit, an extractive distillation subsystem, and a chemical plant demonstrate that this model can further enhance the prediction accuracy.
arXiv Detail & Related papers (2024-02-11T17:40:26Z) - How neural networks learn to classify chaotic time series [77.34726150561087]
We study the inner workings of neural networks trained to classify regular-versus-chaotic time series.
We find that the relation between input periodicity and activation periodicity is key for the performance of LKCNN models.
arXiv Detail & Related papers (2023-06-04T08:53:27Z) - Hardware-aware training for large-scale and diverse deep learning
inference workloads using in-memory computing-based accelerators [7.152059921639833]
We show that many large-scale deep neural networks can be successfully retrained to show iso-accuracy on AIMC.
Our results suggest that AIMC nonidealities that add noise to the inputs or outputs, not the weights, have the largest impact on DNN accuracy.
arXiv Detail & Related papers (2023-02-16T18:25:06Z) - SPIDE: A Purely Spike-based Method for Training Feedback Spiking Neural
Networks [56.35403810762512]
Spiking neural networks (SNNs) with event-based computation are promising brain-inspired models for energy-efficient applications on neuromorphic hardware.
We study spike-based implicit differentiation on the equilibrium state (SPIDE) that extends the recently proposed training method.
arXiv Detail & Related papers (2023-02-01T04:22:59Z) - 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) - Training Feedback Spiking Neural Networks by Implicit Differentiation on
the Equilibrium State [66.2457134675891]
Spiking neural networks (SNNs) are brain-inspired models that enable energy-efficient implementation on neuromorphic hardware.
Most existing methods imitate the backpropagation framework and feedforward architectures for artificial neural networks.
We propose a novel training method that does not rely on the exact reverse of the forward computation.
arXiv Detail & Related papers (2021-09-29T07:46:54Z) - Online Training of Spiking Recurrent Neural Networks with Phase-Change
Memory Synapses [1.9809266426888898]
Training spiking neural networks (RNNs) on dedicated neuromorphic hardware is still an open challenge.
We present a simulation framework of differential-architecture arrays based on an accurate and comprehensive Phase-Change Memory (PCM) device model.
We train a spiking RNN whose weights are emulated in the presented simulation framework, using a recently proposed e-prop learning rule.
arXiv Detail & Related papers (2021-08-04T01:24:17Z) - Inverse-Dirichlet Weighting Enables Reliable Training of Physics
Informed Neural Networks [2.580765958706854]
We describe and remedy a failure mode that may arise from multi-scale dynamics with scale imbalances during training of deep neural networks.
PINNs are popular machine-learning templates that allow for seamless integration of physical equation models with data.
For inverse modeling using sequential training, we find that inverse-Dirichlet weighting protects a PINN against catastrophic forgetting.
arXiv Detail & Related papers (2021-07-02T10:01:37Z) - Training End-to-End Analog Neural Networks with Equilibrium Propagation [64.0476282000118]
We introduce a principled method to train end-to-end analog neural networks by gradient descent.
We show mathematically that a class of analog neural networks (called nonlinear resistive networks) are energy-based models.
Our work can guide the development of a new generation of ultra-fast, compact and low-power neural networks supporting on-chip learning.
arXiv Detail & Related papers (2020-06-02T23:38:35Z)
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.