English
Related papers

Related papers: Linear Reservoir: A Diagonalization-Based Optimiza…

200 papers

We propose zoneout, a novel method for regularizing RNNs. At each timestep, zoneout stochastically forces some hidden units to maintain their previous values. Like dropout, zoneout uses random noise to train a pseudo-ensemble, improving…

Neural and Evolutionary Computing · Computer Science 2017-09-26 David Krueger , Tegan Maharaj , János Kramár , Mohammad Pezeshki , Nicolas Ballas , Nan Rosemary Ke , Anirudh Goyal , Yoshua Bengio , Aaron Courville , Chris Pal

When employing an evolutionary algorithm to optimize a neural networks architecture, developers face the added challenge of tuning the evolutionary algorithm's own hyperparameters - population size, mutation rate, cloning rate, and number…

Neural and Evolutionary Computing · Computer Science 2025-03-17 Benjamin David Winter , William J. Teahan

Humans excel at lifelong learning, as the brain has evolved to be robust to distribution shifts and noise in our ever-changing environment. Deep neural networks (DNNs), however, exhibit catastrophic forgetting and the learned…

Machine Learning · Computer Science 2023-02-23 Fahad Sarfraz , Elahe Arani , Bahram Zonooz

Recurrent neural networks (RNNs) have recently achieved remarkable successes in a number of applications. However, the huge sizes and computational burden of these models make it difficult for their deployment on edge devices. A practically…

Machine Learning · Computer Science 2019-12-10 Liangjian Wen , Xuanyang Zhang , Haoli Bai , Zenglin Xu

Recurrent neural networks (RNNs) can be interpreted as discrete-time state-space models, where the state evolution corresponds to an infinite-impulse-response (IIR) filtering operation governed by both feedforward weights and recurrent…

Machine Learning · Computer Science 2026-02-26 Alexander Morgan , Ummay Sumaya Khan , Lingjia Liu , Lizhong Zheng

Accurate and efficient numerical simulation of unconventional reservoirs is challenging. Long periods of transient flow and steep potential gradients occur due to the extreme conductivity contrast between matrix and fracture. Detailed…

Computational Engineering, Finance, and Science · Computer Science 2020-10-23 Jiamin Jiang

Continuous Time Echo State Networks (CTESNs) are a promising yet under-explored surrogate modeling technique for dynamical systems, particularly those governed by stiff Ordinary Differential Equations (ODEs). A key determinant of the…

Computational Engineering, Finance, and Science · Computer Science 2024-01-25 Saakaar Bhatnagar

We propose an experimental comparison between Deep Echo State Networks (DeepESNs) and gated Recurrent Neural Networks (RNNs) on multivariate time-series prediction tasks. In particular, we compare reservoir and fully-trained RNNs able to…

Machine Learning · Computer Science 2019-11-21 Claudio Gallicchio , Alessio Micheli , Luca Pedrelli

We consider reservoirs in the form of liquid state machines, i.e., recurrently connected networks of spiking neurons with randomly chosen weights. So far only the weights of a linear readout were adapted for a specific task. We wondered…

Neural and Evolutionary Computing · Computer Science 2022-06-15 Anand Subramoney , Franz Scherr , Wolfgang Maass

What is a neural model with minimum architectural complexity that exhibits reasonable language learning capability? To explore such a simple but sufficient neural language model, we revisit a basic reservoir computing (RC) model, Echo State…

Computation and Language · Computer Science 2025-03-04 Ryo Ueda , Tatsuki Kuribayashi , Shunsuke Kando , Kentaro Inui

We present a stochastic first-order optimization method specialized for deep neural networks (DNNs), ECCO-DNN. This method models the optimization variable trajectory as a dynamical system and develops a discretization algorithm that…

Machine Learning · Computer Science 2023-10-24 Carmel Fiscko , Aayushya Agarwal , Yihan Ruan , Soummya Kar , Larry Pileggi , Bruno Sinopoli

This paper proposes a novel approach to improve the performance of distributed nonlinear control systems while preserving stability by leveraging Deep Neural Networks (DNNs). We build upon the Neural System Level Synthesis (Neur-SLS)…

Optimization and Control · Mathematics 2024-08-01 Danilo Saccani , Leonardo Massai , Luca Furieri , Giancarlo Ferrari-Trecate

In this work, we study optimization methods that leverage the linear minimization oracle (LMO) over a norm-ball. We propose a new stochastic family of algorithms that uses the LMO to adapt to the geometry of the problem and, perhaps…

Machine Learning · Computer Science 2025-06-09 Thomas Pethick , Wanyun Xie , Kimon Antonakopoulos , Zhenyu Zhu , Antonio Silveti-Falls , Volkan Cevher

Echo state networks are computationally lightweight reservoir models inspired by the random projections observed in cortical circuitry. As interest in reservoir computing has grown, networks have become deeper and more intricate. While…

Signal Processing · Electrical Eng. & Systems 2019-08-23 Zachariah Carmichael , Humza Syed , Dhireesha Kudithipudi

Adaptive optimization algorithms -- such as Adagrad, Adam, and their variants -- have found widespread use in machine learning, signal processing and many other settings. Several methods in this family are not rotationally equivariant,…

Machine Learning · Computer Science 2026-02-17 Adela DePavia , Jose Cruzado , Jiayou Liang , Vasileios Charisopoulos , Rebecca Willett

Dropout and similar stochastic neural network regularization methods are often interpreted as implicitly averaging over a large ensemble of models. We propose STE (stochastically trained ensemble) layers, which enhance the averaging…

Machine Learning · Computer Science 2019-11-22 Alex Labach , Shahrokh Valaee

Classification models for electroencephalogram (EEG) data show a large decrease in performance when evaluated on unseen test sub jects. We reduce this performance decrease using new regularization techniques during model training. We…

Machine Learning · Computer Science 2023-10-16 Niklas Smedemark-Margulies , Ye Wang , Toshiaki Koike-Akino , Jing Liu , Kieran Parsons , Yunus Bicer , Deniz Erdogmus

This paper investigates how various randomization techniques impact Deep Neural Networks (DNNs). Randomization, like weight noise and dropout, aids in reducing overfitting and enhancing generalization, but their interactions are poorly…

Empirical interpolation method (EIM) is a well-known technique to efficiently approximate parameterized functions. This paper proposes to use EIM algorithm to efficiently reduce the dimension of the training data within supervised machine…

Machine Learning · Computer Science 2023-05-18 Harbir Antil , Madhu Gupta , Randy Price

Conditioning analysis uncovers the landscape of an optimization objective by exploring the spectrum of its curvature matrix. This has been well explored theoretically for linear models. We extend this analysis to deep neural networks (DNNs)…

Computer Vision and Pattern Recognition · Computer Science 2020-07-30 Lei Huang , Jie Qin , Li Liu , Fan Zhu , Ling Shao
‹ Prev 1 8 9 10 Next ›