Deep neural nets approximate random dynamical system trajectories uniformly in time.
problem Approximating trajectories of random dynamical systems over infinite time horizons.
method Recurrent neural networks with simple feedback structures.
result Certain random trajectories can be approximated uniformly in time to any desired accuracy.
SIS-RNN improves model flexibility for sequential data.
problem Limited expressive power of existing stochastic RNNs.
method Semi-implicit variational inference for implicit latent representations.
result SIS-RNN outperforms existing methods in various tasks.
New methods improve Reservoir Computing for chaotic time series prediction.
problem Chaotic time series prediction in Reservoir Computing.
method Established Recurrent Kernel limit, introduced Structured Reservoir Computing.
result Structured Reservoir Computing is faster and more memory-efficient.
A new technique reduces the size of rRNNs for time series prediction.
problem Minimizing the size of rRNNs for efficient time series prediction.
method Combining Takens-based attractor reconstruction with machine learning for feature extraction.
result Reduced network size by a factor of 15 with improved performance.
Recurrent neural networks trained on regular languages exhibit stable states that can recover from noise.
problem Stability of internal states in recurrent neural networks trained on regular languages.
method Empirical study with analysis of network activation and transitions between states.
result Recurrent neural networks trained on regular languages can recover from random perturbations and maintain stable states.
Randomized neural networks use fixed connections for efficiency.
problem Efficiency in deep learning models.
method Fixed connections in neural networks.
result Deep randomized neural networks achieve state-of-the-art results.
New method prunes recurrent networks efficiently, improving performance.
problem Pruning recurrent neural networks (RNNs) is challenging and often leads to poor performance.
method Data-efficient pruning objective derived from the spectrum of the recurrent Jacobian.
result 95% sparse GRUs significantly improve on existing baselines.
Recurrent neural networks have gained widespread use in modeling sequence data across various domains. While many successful recurrent architectures employ a notion of gating, the exact mechanism that enables such remarkable performance is not well understood. We develop a theory for signal propagation in recurrent net…
Recurrent neural networks are a powerful tool, but they are very sensitive to their hyper-parameter configuration. Moreover, training properly a recurrent neural network is a tough task, therefore selecting an appropriate configuration is critical. Varied strategies have been proposed to tackle this issue. However, mos…
Low-complexity spiking networks learn complex tasks with minimal trainable parameters.
problem Training complex reinforcement learning tasks with minimal resources.
method Reinforcement learning on simple networks of spiking neurons with random connections.
result Small random spiking networks achieve learning efficiency similar to humans on complex tasks.
Paper develops a new model for dynamic graph representation learning.
problem Learning over dynamic graphs with changing topology and node attributes.
method Hierarchical variational model with latent random variables and semi-implicit variational inference.
result SI-VGRNN and VGRNN outperform existing methods in dynamic link prediction.
This paper introduces Graph Convolutional Recurrent Network (GCRN), a deep learning model able to predict structured sequences of data. Precisely, GCRN is a generalization of classical recurrent neural networks (RNN) to data structured by an arbitrary graph. Such structured sequences can represent series of frames in v…
Enhances hedging strategies using deep neural networks.
problem Optimizing risks and returns in financial hedging.
method Integrates deep neural networks and random forest classifiers to find optimal hedging strategies.
result Improved hedging strategies with lower costs and risks.
New insights on stability in reservoir computing for better performance.
problem Stability in reservoir computing networks.
method Using the recurrent kernel limit for large reservoir sizes.
result Quantitative characterization of stability and chaos frontier.
Recent studies have suggested that the cognitive process of the human brain is realized as probabilistic inference and can be further modeled by probabilistic graphical models like Markov random fields. Nevertheless, it remains unclear how probabilistic inference can be implemented by a network of spiking neurons in th…
How can local-search methods such as stochastic gradient descent (SGD) avoid bad local minima in training multi-layer neural networks? Why can they fit random labels even given non-convex and non-smooth architectures? Most existing theory only covers networks with one hidden layer, so can we go deeper? In this paper, w…
In this work a novel method to quantify spectral ergodicity for random matrices is presented. The new methodology combines approaches rooted in the metrics of Thirumalai-Mountain (TM) and Kullbach-Leibler (KL) divergence. The method is applied to a general study of deep and recurrent neural networks via the analysis of…
Interneurons improve learning in neural networks by accelerating convergence.
problem Rapid adaptation to changing input statistics in neural networks.
method Two mathematically tractable recurrent linear neural networks were compared: one with direct recurrent connections and the other with interneurons that mediate recurrent communication.
result The network with interneurons converges more quickly than the network with direct recurrent connections, scaling logarithmically with initialization spectrum.
QRPNNs use quaternion-valued recurrent correlation neural networks to solve cross-talk issues.
problem Cross-talk problem in QRCNNs.
method Combining non-local projection learning with QRCNNs.
result QRPNNs exhibit greater storage capacity and noise tolerance.
RecNets use RNNs to process image channels in a compact, recurrent way.
problem Creating efficient neural network architectures for computer vision.
method Introducing RecNets with CRC layers that simulate recurrent processing of image channels.
result RecNets achieve superior size-accuracy trade-off compared to other compact models.
Neural networks with learned biases can approximate any function.
problem Whether neural networks with only learned biases can approximate any continuous function.
method Theoretical and numerical analysis of random weights and learned biases in neural networks.
result Feedforward and recurrent neural networks with random weights can approximate any continuous function and dynamical systems.
Paper uses AI to predict medications from medical codes, improving accuracy in healthcare.
problem Predicting medications from incomplete or incorrect medical codes is challenging.
method Robust Recurrent Neural Networks (RNNs) with decay mechanism and noise injection.
result The method accurately predicts medication orders from contaminated medical codes.
Modern smart grids rely on advanced metering infrastructure (AMI) networks for monitoring and billing purposes. However, such an approach suffers from electricity theft cyberattacks. Different from the existing research that utilizes shallow, static, and customer-specific-based electricity theft detectors, this paper p…
This paper improves RNN generalization without normalization conditions.
problem Generalization of over-parameterized RNNs without normalization constraints.
method Detailed analysis of neural tangent kernel matrix for improved generalization bounds.
result RNNs can learn functions without normalization conditions and with almost-polynomial scaling in input length.
Recurrent neural network (RNN)'s architecture is a key factor influencing its performance. We propose algorithms to optimize hidden sizes under running time constraint. We convert the discrete optimization into a subset selection problem. By novel transformations, the objective function becomes submodular and constrain…
Paper presents FPGA implementation for efficient recurrent neural networks.
problem Implementing recurrent neural networks on FPGAs for low latency.
method Developed hls4ml framework to implement LSTM and GRU layers.
result Demonstrated effective designs for both small and large models.
Probabilistic models predict neural network performance across varying hyperparameters.
problem Predicting neural network performance with different hyperparameters.
method Probabilistic models based on random forests and Bayesian recurrent neural networks.
result Models outperform state-of-the-art hyperparameter optimization methods.
Scalable verifier for recurrent neural networks using polyhedral abstractions.
problem Certifying the correctness of recurrent neural networks.
method Combining sampling, optimization, and Fermat's theorem for polyhedral abstractions; gradient descent for refinement.
result Successfully verified challenging recurrent models in various domains.
This paper analyzes the generalization risk of unrolled neural networks using Stein's Unbiased Risk Estimator.
problem Analyzing the generalization risk of unrolled neural networks and its relationship to network design and train sample size.
method Using Stein's Unbiased Risk Estimator (SURE), the paper analyzes the generalization risk with bias and variance components for recurrent unrolled networks, focusing on the degrees-of-freedom (DOF) component and the trace of the end-to-end network Jacobian.
result DOF is well-approximated by the weighted path sparsity of the network under incoherence conditions on the trained weights, and DOF increases with train sample size and converges to the generalization risk for both recurrent and non-recurrent schemes.
Nonlinear RNNs' memory capacity varies widely, making it impractical.
problem The usefulness of memory capacity as a metric for linear RNNs is questioned.
method Analysis of random nonlinear RNNs with varying input scales.
result Memory capacity of nonlinear RNNs is arbitrary and impractical.
Understanding how neural networks learn remains one of the central challenges in machine learning research. From random at the start of training, the weights of a neural network evolve in such a way as to be able to perform a variety of tasks, like classifying images. Here we study the emergence of structure in the wei…
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.
Bayesian approach improves neural network recurrence.
problem Improving neural network recurrence mechanisms.
method Introducing Bayesian recurrence relations and gates.
result Bayesian approach can perform as well as or better than conventional recurrent networks.
DCRNN improves LSTM for chaotic dynamical system forecasting.
problem Modeling chaotic dynamical systems with recurrent neural networks.
method DCRNN incorporates learnable skip-connections and a Lyapunov stability regularization term.
result DCRNN outperforms LSTM in 100 out of 100 experiments, reducing mean squared error by 80.0%.
Study Gaussian-process limits of neural networks using tensor programs.
problem Understanding the behavior of neural networks as they approach infinite width.
method Quantitative analysis through tensor programs and Wasserstein distance.
result Explicit finite-width error bounds, showing convergence to Gaussian-process limits.
Time series forecasting is difficult. It is difficult even for recurrent neural networks with their inherent ability to learn sequentiality. This article presents a recurrent neural network based time series forecasting framework covering feature engineering, feature importances, point and interval predictions, and for…
End-to-end training of recurrent neural networks for biological sequences.
problem Training recurrent neural networks for biological sequence classification.
method Generalized convolutional kernel networks with recurrent structures.
result Outperforms existing methods for protein classification tasks.
Study uses RNN to detect CPs with SI to control false positives.
problem Detecting false positives in RNN-based change point detection.
method Introduces Selective Inference (SI) framework to RNN for CP detection.
result Valid p-values for CPs detected by RNN reduce false positives.
Oja's rule improves neural network training without engineered tricks.
problem Training deep neural networks with biological constraints.
method Incorporating Oja's plasticity rule into error-driven training.
result Stable, efficient learning in feedforward and recurrent architectures.
Recurrent neural networks show state-of-the-art results in many text analysis tasks but often require a lot of memory to store their weights. Recently proposed Sparse Variational Dropout eliminates the majority of the weights in a feed-forward neural network without significant loss of quality. We apply this technique …
Recurrent Neural Networks (RNNs) are designed to handle sequential data but suffer from vanishing or exploding gradients. Recent work on Unitary Recurrent Neural Networks (uRNNs) have been used to address this issue and in some cases, exceed the capabilities of Long Short-Term Memory networks (LSTMs). We propose a simp…
How can we efficiently propagate uncertainty in a latent state representation with recurrent neural networks? This paper introduces stochastic recurrent neural networks which glue a deterministic recurrent neural network and a state space model together to form a stochastic and sequential neural generative model. The c…
RANP improves neural processes for sequential data.
problem Capturing temporal order and recurrent structure from sequential data.
method Incorporated ANP into a recurrent neural network.
result RANP outperforms NPs and LSTMs in 1D regression and autonomous-driving tasks.
Optimal stock price prediction model using recurrent neural networks with RMSprop optimizer.
problem Stock price prediction using neural networks.
method Comparison of fully connected, convolutional, and recurrent architectures; inclusion of three optimization techniques.
result Single layer recurrent neural network with RMSprop optimizer produces optimal results with validation and test MAE of 0.0150 and 0.0148 respectively.
Leveraging advances in variational inference, we propose to enhance recurrent neural networks with latent variables, resulting in Stochastic Recurrent Networks (STORNs). The model i) can be trained with stochastic gradient methods, ii) allows structured and multi-modal conditionals at each time step, iii) features a re…
Traditional Recurrent Neural Networks assume vectorized data as inputs. However many data from modern science and technology come in certain structures such as tensorial time series data. To apply the recurrent neural networks for this type of data, a vectorisation process is necessary, while such a vectorisation leads…
Sleep disorders are implicated in a growing number of health problems. In this paper, we present a signal-processing/machine learning approach to detecting arousals in the multi-channel polysomnographic recordings of the Physionet/CinC Challenge2018 dataset. Methods: Our network architecture consists of two components.…
Spatiotemporal forecasting has various applications in neuroscience, climate and transportation domain. Traffic forecasting is one canonical example of such learning task. The task is challenging due to (1) complex spatial dependency on road networks, (2) non-linear temporal dynamics with changing road conditions and (…