Agnostic Physics-Driven Deep Learning
This work establishes that a physical system can perform statistical learning without gradient computations, via an Agnostic Equilibrium Propagation (Aeqprop) procedure that combines energy minimization, homeostatic control, and nudging towards the correct response. In Aeqprop, the specifics of the system do not have to be known: the procedure is based only on external manipulations, and produces a stochastic gradient descent without explicit gradient computations. Thanks to nudging, the system performs a true, order-one gradient step for each training sample, in contrast with order-zero methods like reinforcement or evolutionary strategies, which rely on trial and error. This procedure considerably widens the range of potential hardware for statistical learning to any system with enough controllable parameters, even if the details of the system are poorly known. Aeqprop also establishes that in natural (bio)physical systems, genuine gradient-based statistical learning may result from generic, relatively simple mechanisms, without backpropagation and its requirement for analytic knowledge of partial derivatives.
Code (0)
등록된 구현이 없습니다.
Tasks
Deep LearningSimilar Papers 제목 키워드 기반
Physics-informed State-space Neural Networks for Transport Phenomena
This work introduces Physics-informed State-space neural network Models (PSMs), a novel solution to achieving real-time optimization, flexibility, and fault tolerance in autonomous systems, particularly in transport-domi…
DiagnosticFault DetectionRAWild: Sensor-Agnostic RAW Object Detection via Physics-Guided Curve and Grid Modeling
Camera sensor RAW data offers intrinsic advantages for object detection, including deeper bit depth, preserved physical information, and freedom from image signal processor (ISP) distortions. However, varying exposure co…
Object DetectionDiagnostics Using Nuclear Plant Cyber Attack Analysis Toolkit
A Python interface is developed for the GPWR Simulator to automatically simulate cyber-spoofing of different steam generator parameters and plant operation. Specifically, steam generator water level, feedwater flowrate, …
Anomaly DetectionScatterPrism: convergence for generative simulation and inverse problems in particle and nuclear physics
High-fidelity simulations and complex inverse problems, such as detector modeling and unfolding, are computationally intensive bottlenecks across subatomic physics, yet essential for accurate physical interpretation. Whi…
Supervised learning from noisy observations: Combining machine-learning techniques with data assimilation
Data-driven prediction and physics-agnostic machine-learning methods have attracted increased interest in recent years achieving forecast horizons going well beyond those to be expected for chaotic dynamical systems. In …
BIG-bench Machine Learning