Machine Learning Driven Global Optimisation Framework for Analog Circuit Design

• URL: http://arxiv.org/abs/2404.02911v2
• Date: Mon, 14 Oct 2024 23:44:11 GMT
• Title: Machine Learning Driven Global Optimisation Framework for Analog Circuit Design
• Authors: Ria Rashid, Komala Krishna, Clint Pazhayidam George, Nandakumar Nambath,
• Abstract summary: We propose a machine learning-driven optimisation framework for analog circuit design. We employ machine learning models and spice simulations to direct the optimisation algorithm.
• Score: 0.0
• License:
• Abstract: We propose a machine learning-driven optimisation framework for analog circuit design in this paper. The primary objective is to determine the device sizes for the optimal performance of analog circuits for a given set of specifications. Our methodology entails employing machine learning models and spice simulations to direct the optimisation algorithm towards achieving the optimal design for analog circuits. Machine learning based global offline surrogate models, with the circuit design parameters as the input, are built in the design space for the analog circuits under study and is used to guide the optimisation algorithm, resulting in faster convergence and a reduced number of spice simulations. Multi-layer perceptron and random forest regressors are employed to predict the required design specifications of the analog circuit. Since the saturation condition of transistors is vital in the proper working of analog circuits, multi-layer perceptron classifiers are used to predict the saturation condition of each transistor in the circuit. The feasibility of the candidate solutions is verified using machine learning models before invoking spice simulations. We validate the proposed framework using three circuit topologies--a bandgap reference, a folded cascode operational amplifier, and a two-stage operational amplifier. The simulation results show better optimum values and lower standard deviations for fitness functions after convergence. Incorporating the machine learning-based predictions proposed in the optimisation method has resulted in the reduction of spice calls by 56%, 59%, and 83% when compared with standard approaches in the three test cases considered in the study.

Related papers

• Automated Placement of Analog Integrated Circuits using Priority-based Constructive Heuristic [0.0]
  We focus on the specific class of analog placement, which requires so-called pockets, their possible merging, and parametrizable minimum distances between devices. Our solution minimizes the perimeter of the circuit's bounding box and the approximated wire length. We show the quality of the proposed method on both synthetically generated and real-life industrial instances accompanied by manually created designs.
  arXiv  Detail & Related papers  (2024-10-18T07:16:59Z)
• LaMAGIC: Language-Model-based Topology Generation for Analog Integrated Circuits [17.002169206594793]
  We introduce LaMAGIC, a pioneering language model-based topology generation model. LaMAGIC can efficiently generate an optimized circuit design from the custom specification in a single pass. LaMAGIC achieves a success rate of up to 96% under a strict tolerance of 0.01.
  arXiv  Detail & Related papers  (2024-07-19T22:51:41Z)
• Finding Transformer Circuits with Edge Pruning [71.12127707678961]
  We propose Edge Pruning as an effective and scalable solution to automated circuit discovery. Our method finds circuits in GPT-2 that use less than half the number of edges compared to circuits found by previous methods. Thanks to its efficiency, we scale Edge Pruning to CodeLlama-13B, a model over 100x the scale that prior methods operate on.
  arXiv  Detail & Related papers  (2024-06-24T16:40:54Z)
• Learning to Design Analog Circuits to Meet Threshold Specifications [2.5818330243826924]
  We propose a method for generating from simulation data a dataset on which a system can be trained to design circuits to meet threshold specifications. We show that our method consistently reaches success rate better than 90% at 5% error margin, while also improving data efficiency by upward of an order of magnitude.
  arXiv  Detail & Related papers  (2023-07-25T23:25:05Z)
• Transformers as Statisticians: Provable In-Context Learning with In-Context Algorithm Selection [88.23337313766353]
  This work first provides a comprehensive statistical theory for transformers to perform ICL. We show that transformers can implement a broad class of standard machine learning algorithms in context. A emphsingle transformer can adaptively select different base ICL algorithms.
  arXiv  Detail & Related papers  (2023-06-07T17:59:31Z)
• End-to-End Meta-Bayesian Optimisation with Transformer Neural Processes [52.818579746354665]
  This paper proposes the first end-to-end differentiable meta-BO framework that generalises neural processes to learn acquisition functions via transformer architectures. We enable this end-to-end framework with reinforcement learning (RL) to tackle the lack of labelled acquisition data.
  arXiv  Detail & Related papers  (2023-05-25T10:58:46Z)
• Domain Knowledge-Infused Deep Learning for Automated Analog/Radio-Frequency Circuit Parameter Optimization [6.599793419469274]
  This paper presents a reinforcement learning method to automate the analog circuit parameter optimization. It is inspired by human experts who rely on domain knowledge of analog circuit design. Experimental results on exemplary circuits show it achieves human-level design accuracy (99%) 1.5X efficiency of existing best-performing methods.
  arXiv  Detail & Related papers  (2022-04-27T13:58:51Z)
• Pretraining Graph Neural Networks for few-shot Analog Circuit Modeling and Design [68.1682448368636]
  We present a supervised pretraining approach to learn circuit representations that can be adapted to new unseen topologies or unseen prediction tasks. To cope with the variable topological structure of different circuits we describe each circuit as a graph and use graph neural networks (GNNs) to learn node embeddings. We show that pretraining GNNs on prediction of output node voltages can encourage learning representations that can be adapted to new unseen topologies or prediction of new circuit level properties.
  arXiv  Detail & Related papers  (2022-03-29T21:18:47Z)
• Domain Knowledge-Based Automated Analog Circuit Design with Deep Reinforcement Learning [6.599793419469274]
  This paper presents a deep reinforcement learning method to expedite the design of analog circuits. Experimental results show it achieves human-level design accuracy (99%) with 1.5x efficiency of existing best-performing methods.
  arXiv  Detail & Related papers  (2022-02-26T16:56:45Z)
• Machine Learning Framework for Quantum Sampling of Highly-Constrained, Continuous Optimization Problems [101.18253437732933]
  We develop a generic, machine learning-based framework for mapping continuous-space inverse design problems into surrogate unconstrained binary optimization problems. We showcase the framework's performance on two inverse design problems by optimizing thermal emitter topologies for thermophotovoltaic applications and (ii) diffractive meta-gratings for highly efficient beam steering.
  arXiv  Detail & Related papers  (2021-05-06T02:22:23Z)
• An AI-Assisted Design Method for Topology Optimization Without Pre-Optimized Training Data [68.8204255655161]
  An AI-assisted design method based on topology optimization is presented, which is able to obtain optimized designs in a direct way. Designs are provided by an artificial neural network, the predictor, on the basis of boundary conditions and degree of filling as input data.
  arXiv  Detail & Related papers  (2020-12-11T14:33:27Z)

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.