New deep ESN architectures improve memory capacity and prediction accuracy.
problem Improving memory capacity and prediction accuracy of ESNs.
method Two new deep ESN architectures: parallel and series. Analysis of memory capacity and prediction accuracy.
result Parallel deep ESNs have equivalent memory capacity to shallow ESNs, while series deep ESNs have smaller memory capacity.
New method combines long-memory reservoirs for accurate dengue forecasting from short data.
problem Accurate dengue forecasting from short, noisy, non-stationary, and nonlinear data.
method Fractional ESN and Wavelet ESN frameworks integrating long-term memory.
result fESN and wESN outperform baselines in multiple dengue datasets and forecasting horizons.
We analyze generalization in deep learning models using random matrix theory.
problem Understanding the generalization error in deep learning models with random feature representations.
method Applying Random Matrix Theory to derive asymptotic generalization error formulas for various architectures.
result Linear ESNs are equivalent to ridge regression with exponentially time-weighted input covariance, revealing an inductive bias towards recent inputs.
ESN model helps understand climate event impacts.
problem Understanding complex climate event impacts.
method Feature importance methods for ESNs on spatio-temporal climate data.
result Characterized relationships between Mount Pinatubo eruption variables.
Deep models predict intraday electricity prices accurately.
problem Accurately forecasting intraday electricity prices.
method Two deep time series probabilistic models using ESNs with stochastic disturbances and copulas.
result Deep distributional models provide accurate short-term probabilistic price forecasts.
We propose a physics-informed Echo State Network (ESN) to predict the evolution of chaotic systems. Compared to conventional ESNs, the physics-informed ESNs are trained to solve supervised learning tasks while ensuring that their predictions do not violate physical laws. This is achieved by introducing an additional lo…
Deep learning models predict chaotic Lorenz 96 system accurately.
problem Predicting short-term and long-term statistics of a multi-scale chaotic system.
method Reservoir computing (RC-ESN), ANN, RNN-LSTM.
result RC-ESN outperforms ANN and RNN-LSTM for short-term prediction.
ESNs trained with Tikhonov least squares approximate ergodic dynamical systems in L2(μ) norm.
problem Approximating ergodic dynamical systems using ESNs.
method Tikhonov least squares regression on ESNs trained on observations from an ergodic dynamical system.
result ESNs trained with Tikhonov least squares approximate the target function in the L2(μ) norm.
Long-lead forecasting for spatio-temporal systems can often entail complex nonlinear dynamics that are difficult to specify it a priori. Current statistical methodologies for modeling these processes are often highly parameterized and thus, challenging to implement from a computational perspective. One potential parsim…
Echo State Networks (ESNs) are recurrent neural networks that only train their output layer, thereby precluding the need to backpropagate gradients through time, which leads to significant computational gains. Nevertheless, a common issue in ESNs is determining its hyperparameters, which are crucial in instantiating a …
New analysis reveals optimal regularization for ESNs, avoiding double descent.
problem Characterizing and optimizing Echo State Networks (ESNs) for precise bias-variance.
method Random matrix theory applied to ESNs in a teacher-student setting.
result ESNs achieve lower MSE with limited training samples and teacher memory.
Feedback improves ESN performance by 30-60% across various tasks.
problem Reducing computational complexity in ESNs for complex sequential data processing.
method State feedback to modify the internal reservoir state of ESNs.
result Feedback significantly improves ESN performance, reducing error by 30-60%.
Echo State Networks (ESN) are a class of Recurrent Neural Networks (RNN) that has gained substantial popularity due to their effectiveness, ease of use and potential for compact hardware implementation. An ESN contains the three network layers input, reservoir and readout where the reservoir is the truly recurrent netw…
Efficient cross-validation method for Echo State Networks reduces validation time complexity.
problem Hyper-parameter tuning and validation for Echo State Networks (ESNs).
method Proposes several k-fold cross-validation schemes for ESNs with an efficient algorithm. result Cross-validation of ESNs can be done for the same time complexity as a single split validation.
Optical ESNs enable flexible, efficient machine learning with reduced energy.
problem Implementing universal computational capabilities in machine learning.
method Optical implementation of ESNs leveraging stimulated Brillouin scattering.
result Efficient, scalable, and memory-capable optical reservoir computing.
Echo state networks are powerful recurrent neural networks. However, they are often unstable and shaky, making the process of finding an good ESN for a specific dataset quite hard. Obtaining a superb accuracy by using the Echo State Network is a challenging task. We create, develop and implement a family of predictably…
ESNs with transfer learning predict long-term chaotic patterns in spatiotemporal dynamical systems.
problem Predicting long-term statistical patterns of spatiotemporally chaotic dynamical systems.
method Echo state networks (ESNs) with transfer learning.
result ESNs with transfer learning accurately predict long-term statistical properties of spatiotemporally chaotic PDEs.
Study shows structured reservoirs improve deep ESN performance.
problem Improving performance of deep reservoir computing networks.
method Investigated structured reservoir topologies in deep ESNs.
result Structured reservoirs significantly enhance predictive performance.
Machine learning predicts dam-break flood wave behavior accurately.
problem Predicting long-term wave behavior in dam-break floods.
method Solved Saint-Venant equations using Lax-Wendroff scheme, trained RC-ESN with flow depth data.
result RC-ESN model predicts 286 time-steps ahead with RMSE < 0.01, outperforming LSTM.
Efficient CV for ESNs improves time series predictions.
problem Lack of CV in time series modeling, especially for ESNs.
method Two-level optimizations for k-fold CV of ESNs. result Proposed CV schemes give better and more stable test performance.
Echo state network (ESN) is viewed as a temporal non-orthogonal expansion with pseudo-random parameters. Such expansions naturally give rise to regressors of various relevance to a teacher output. We illustrate that often only a certain amount of the generated echo-regressors effectively explain the variance of the tea…
Recurrent neural networks (RNNs) have drawn interest from machine learning researchers because of their effectiveness at preserving past inputs for time-varying data processing tasks. To understand the success and limitations of RNNs, it is critical that we advance our analysis of their fundamental memory properties. W…
ESN models predict intraday stock returns efficiently.
problem Intraday stock return prediction using machine learning.
method Echo State Network (ESN) models with random parameters.
result ESN models achieve strong forecasting performance efficiently.
New framework analyzes temporal features in state space models.
problem Understanding temporal dependencies in data streams.
method Proposes a framework for rigorous analysis of state representations in ESNs, using temporal feature spaces and kernel machines.
result Phase transition in kernel richness for cycle reservoir topology.
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 represent signals featured by multiple time-scales dynamics. The analysis is perfo…
Spatially aware ESN detects anomalies in chaotic time series.
problem Automated anomaly detection in chaotic time series, especially turbulent ocean simulations.
method Extended Echo State Network with spatially aware input maps and loss function.
result Spatial ESN reduces anomaly detection to thresholding of prediction error.
SORSCNs improve nonstationary data modeling by self-organizing and adjusting network parameters.
problem Nonstationary data challenges traditional models in continuous learning.
method SORSCNs autonomously adjust network parameters and structure in real-time using adaptive algorithms.
result SORSCNs outperform other models in generalizing to nonstationary data.
Reservoir Computing (RC) refers to a Recurrent Neural Networks (RNNs) framework, frequently used for sequence learning and time series prediction. The RC system consists of a random fixed-weight RNN (the input-hidden reservoir layer) and a classifier (the hidden-output readout layer). Here we focus on the sequence lear…
Spatio-temporal data and processes are prevalent across a wide variety of scientific disciplines. These processes are often characterized by nonlinear time dynamics that include interactions across multiple scales of spatial and temporal variability. The data sets associated with many of these processes are increasing …
CogScale benchmarks AI architectures for sequential processing.
problem Evaluating AI architectures' ability to process sequential information efficiently.
method 14 scalable synthetic tasks designed to isolate cognitive and memory abilities at different scales.
result Attention mechanisms and modern state-space models consistently maintain high performance as task difficulty scales.
HFNO enhances interpretability of turbulent flows through parallel wavenumber bin processing.
problem Opaque inner workings of Fourier Neural Operators (FNOs) hinder physical interpretability.
method Introduces HFNO, a novel FNO-based architecture that processes wavenumber bins in parallel, enhancing interpretability.
result HFNO decomposes turbulent flows across various scales, enabling increased interpretability and multiscale modeling.
Probabilistic deep learning uses neural networks and models to handle uncertainty.
problem Handling uncertainty in deep learning models.
method Two approaches: probabilistic neural networks and deep probabilistic models.
result TensorFlow Probability library supports both approaches.
Improves deep learning robustness by considering task and model.
problem Adversarial attacks on deep learning systems.
method Binary and interval label encoding strategy to redefine classification tasks and design corresponding loss functions.
result Our method enhances robustness without sacrificing accuracy.
Deep-RLS uses deep learning to improve PCA for better source separation.
problem Improving PCA for better source separation in nonlinear systems.
method Inspired by RLS, Deep-RLS unfolds RLS iterations into a deep neural network.
result Deep-RLS significantly improves accuracy in recovering source signals.
How to understand deep learning systems remains an open problem. In this paper we propose that the answer may lie in the geometrization of deep networks. Geometrization is a bridge to connect physics, geometry, deep network and quantum computation and this may result in a new scheme to reveal the rule of the physical w…
Paper interprets deep learning using decision trees and Haar wavelets.
problem Understanding the function approximation capabilities of ReLU deep learning.
method Constructing a deep learning structure equivalent to a forest and approximating Haar wavelet functions with ReLU deep learning.
result ReLU deep learning can be considered as decision trees and approximates Haar wavelet functions with arbitrary precision.
Deep learning models can discriminate against certain groups, requiring computational methods to ensure fairness.
problem Algorithmic discrimination in deep learning models affecting protected groups.
method Interpretability and mitigation approaches at different stages of deep learning lifecycle.
result Interpretability aids in diagnosing and mitigating algorithmic discrimination in deep learning.
Deep learning methods improve overlapping speaker separation across languages and noise.
problem Overlapping speaker separation in realistic scenarios.
method Deep clustering and deep attractor networks.
result Deep learning methods are effective for a broad range of languages and can handle untrained languages with common features.
SDF adapts Deep Forest for evolving data streams with active learning.
problem Adapting Deep Forest for evolving data streams.
method Streaming Deep Forest (SDF) with Augmented Variable Uncertainty (AVU) active learning.
result SDF with AVU outperforms other methods trained with all instances by 70% labeling budget.
Deep SSMs use neural networks to identify complex systems.
problem Identifying nonlinear systems with high uncertainty.
method Deep state space models with neural networks.
result Deep SSMs outperform traditional methods on benchmarks.
The great success of deep learning shows that its technology contains profound truth, and understanding its internal mechanism not only has important implications for the development of its technology and effective application in various fields, but also provides meaningful insights into the understanding of human brai…
DSCF-Net learns deep features for clustering with robustness and locality preservation.
problem Unsupervised deep representation learning for clustering.
method Integrates robust deep concept factorization, deep self-expressive representation, and adaptive locality preserving feature learning.
result Delivers state-of-the-art performance on public databases.
Bayesian methods enhance deep learning models by improving reliability and uncertainty.
problem Improving reliability and uncertainty awareness in deep learning models.
method Approximate Bayesian inference techniques, including SG-MCMC and VI, applied to deep learning models.
result Enhanced posterior inference for deep learning models, particularly in neural networks and generative models.
NeurIPS 2020 competition seeks to predict deep learning generalization.
problem Understanding and predicting generalization in deep learning models.
method Propose complexity measures to accurately predict generalization performance.
result A robust complexity measure could improve deep learning reliability.
This paper analyzes generalization issues in deep reinforcement learning.
problem Understanding and improving generalization capabilities of deep reinforcement learning policies.
method Formalizing and categorizing solutions to address overfitting in deep reinforcement learning.
result A comprehensive analysis of generalization challenges and solutions in deep reinforcement learning.
This paper explains why ResNets generalize better than FFNets using neural tangent kernels.
problem Understanding why deep ResNets generalize better than deep FFNets.
method Using neural tangent kernels to compare the learnability of functions induced by the kernels of ResNets and FFNets.
result The kernel of ResNets does not exhibit degeneracy as depth increases, unlike FFNets.
This paper provides an overview of deep semi-supervised learning methods.
problem Reducing the need for large annotated datasets in deep learning.
method Summarizes dominant semi-supervised approaches in deep learning.
result Provides a comprehensive overview of deep semi-supervised learning.
Deep learning is very effective at jointly learning feature representations and classification models, especially when dealing with high dimensional input patterns. Probabilistic logic reasoning, on the other hand, is capable to take consistent and robust decisions in complex environments. The integration of deep learn…