A novel Deep Neural Network architecture for non-linear system identification
We present a novel Deep Neural Network (DNN) architecture for non-linear system identification. We foster generalization by constraining DNN representational power. To do so, inspired by fading memory systems, we introduce inductive bias (on the architecture) and regularization (on the loss function). This architecture allows for automatic complexity selection based solely on available data, in this way the number of hyper-parameters that must be chosen by the user is reduced. Exploiting the highly parallelizable DNN framework (based on Stochastic optimization methods) we successfully apply our method to large scale datasets.
Code (0)
등록된 구현이 없습니다.
Tasks
Inductive BiasStochastic OptimizationSimilar Papers 제목 키워드 기반
dynoNet: a neural network architecture for learning dynamical systems
This paper introduces a network architecture, called dynoNet, utilizing linear dynamical operators as elementary building blocks. Owing to the dynamical nature of these blocks, dynoNet networks are tailored for sequence …
Direct identification of continuous-time linear switched state-space models
This paper presents an algorithm for direct continuous-time (CT) identification of linear switched state-space (LSS) models. The key idea for direct CT identification is based on an integral architecture consisting of an…
State Space ModelsBilinear residual Neural Network for the identification and forecasting of dynamical systems
Due to the increasing availability of large-scale observation and simulation datasets, data-driven representations arise as efficient and relevant computation representations of dynamical systems for a wide range of appl…
Deep Convolutional Networks in System Identification
Recent developments within deep learning are relevant for nonlinear system identification problems. In this paper, we establish connections between the deep learning and the system identification communities. It has rece…
Deep LearningMultiregion Bilinear Convolutional Neural Networks for Person Re-Identification
In this work we propose a new architecture for person re-identification. As the task of re-identification is inherently associated with embedding learning and non-rigid appearance description, our architecture is based o…
Person Re-Identification