nmODE: neural memory ordinary differential equation
نویسندگان
چکیده
Abstract Brain neural networks are regarded as dynamical systems in science, which memories interpreted attractors of the systems. Mathematically, ordinary differential equations (ODEs) can be utilized to describe Any ODE that is employed dynamics a network called neuralODE. Inspired by rethinking nonlinear representation ability existing artificial together with functions columns neocortex, this paper proposes theory memory-based neuralODE, composed two novel models: nmODE and $$\epsilon$$ ϵ -net, learning algorithms: nmLA -LA. The (neural memory Ordinary Differential Equation) designed special structure separates neurons from neurons, making its clear. Given any external input, possesses global attractor property thus embedded mechanism. establishes mapping input associated does not have problem features homeomorphic data space, occurs frequently most neuralODEs. Learning Algorithm) developed proposing an interesting three-dimensional inverse (invODE) has advantages parameter efficiency. proposed -net discrete version nmODE, particularly feasible for digital computing. -LA ( algorithm) requires no prior knowledge number layers. Both gradient vanishing. Experimental results show comparable state-of-the-art methods.
منابع مشابه
A Universal Ordinary Differential Equation
An astonishing fact was established by Lee A. Rubel in 81: there exists a fixed non-trivial fourthorder polynomial differential algebraic equation (DAE) such that for any positive continuous function φ on the reals, and for any positive continuous function (t), it has a C∞ solution with |y(t) − φ(t)| < (t) for all t. Lee A. Rubel provided an explicit example of such a polynomial DAE. Other exam...
متن کاملAPPLICATION NEURAL NETWORK TO SOLVE ORDINARY DIFFERENTIAL EQUATIONS
In this paper, we introduce a hybrid approach based on neural network and optimization teqnique to solve ordinary differential equation. In proposed model we use heyperbolic secont transformation function in hiden layer of neural network part and bfgs teqnique in optimization part. In comparison with existing similar neural networks proposed model provides solutions with high accuracy. Numerica...
متن کاملSparse Estimation in Ordinary Differential Equation Systems
Ordinary differential equation systems are used to model abundances of chemical species as deterministic continuous time processes. Identification of the system from noisy data is a major challenge with applications in systems biology – such as to the inference of phosphoprotein interaction networks as in [3]. For mass action kinetics the system structure – the network – is encoded via sparsity...
متن کاملRobust estimation for ordinary differential equation models.
Applied scientists often like to use ordinary differential equations (ODEs) to model complex dynamic processes that arise in biology, engineering, medicine, and many other areas. It is interesting but challenging to estimate ODE parameters from noisy data, especially when the data have some outliers. We propose a robust method to address this problem. The dynamic process is represented with a n...
متن کاملAiry equation with memory involvement via Liouville differential operator
In this work, a non-integer order Airy equation involving Liouville differential operator is considered. Proposing an undetermined integral solution to the left fractional Airy differential equation, we utilize some basic fractional calculus tools to clarify the closed form. A similar suggestion to the right FADE, converts it into an equation in the Laplace domain. An illustration t...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Artificial Intelligence Review
سال: 2023
ISSN: ['0269-2821', '1573-7462']
DOI: https://doi.org/10.1007/s10462-023-10496-2