Deep RL model learns 2.5D fighting games with height ambiguity.
problem Ambiguity in character height/depth and sequential action orders in 2.5D fighting games.
method Modified A3C network with Recurrent Info network for combo skill observation.
result Successfully learned and played Little Fighter 2 (LF2) 2.5D fighting game.
New method predicts Parkinson's using deep neural network latent info.
problem Medical diagnosis of Parkinson's disease.
method Transfer learning, k-means clustering, k-Nearest Neighbour classification of DNN representations.
result Improved prediction of Parkinson's disease based on MRI and DaT Scan data.
Introduces info intervention to handle causal questions and check counterfactual variables.
problem Controversial interpretation of causal questions for non-manipulable variables and lack of power to check counterfactual variables.
method Intervenes input/output information of causal mechanisms, providing causal diagrams for communication and theoretical focus.
result Causal diagrams based on info intervention provide a new perspective on information transfer as causality.
We present an information-theoretic framework for sequential adaptive compressed sensing, Info-Greedy Sensing, where measurements are chosen to maximize the extracted information conditioned on the previous measurements. We show that the widely used bisection approach is Info-Greedy for a family of k-sparse signals b…
Proper balance between exploitation and exploration is what makes good decisions, which achieve high rewards like payoff or evolutionary fitness. The Infomax principle postulates that maximization of information directs the function of diverse systems, from living systems to artificial neural networks. While specific a…
Estimates non-parametric logistic model using case-control data and external summary info.
problem Imbalanced binary data in case-control studies.
method Two-step estimation procedure with deep neural network for functional approximation.
result Proposed estimator achieves optimal convergence rate in non-parametric regression.
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.
Unified recurrent networks reveal differences in complexity levels of grammars.
problem Understanding the complexity and behavior of recurrent networks.
method Connecting recurrent networks with deterministic finite automata and formal grammars.
result Unified recurrent networks improve performance and match grammars from different complexity levels.
Stable recurrent models perform similarly to unstable ones, proving useful for sequence tasks.
problem The lack of stability in recurrent neural networks hinders their practical application.
method Theoretical analysis and empirical testing of stable recurrent models.
result Stable recurrent models can be well approximated by feed-forward networks, performing similarly to unstable ones.
New method uses mutual info and network science to explain deep learning models.
problem Interpreting deep neural networks for understanding their decision-making process.
method Coupling mutual information with network science to quantify information flow in deep learning models.
result Proposed NIF technique for codifying information flow in deep learning models.
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.
Recurrent neural networks improve time series forecasting accuracy.
problem Time series forecasting is challenging, especially for sequential data.
method A recurrent neural network framework for feature engineering, prediction, and evaluation is presented.
result The LSTM and GRU networks outperform traditional methods in forecasting accuracy.
Batch-normalized RHN improves gradient control in recurrent networks.
problem Gradient vanishing or exploding in recurrent networks.
method Batch normalization applied at each recurrence loop in RHN.
result Batch-normalized RHN converges faster and performs better.
Improved semantic segmentation accuracy by addressing class imbalance.
problem Class imbalance in training data leads to misclassification of rare classes.
method Localized weighting of posterior class probabilities with pixel-wise priors.
result Significant improvement in recall and reduction of non-detection rate for rare classes.
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.
This work optimizes reservoir computing models by linking recurrence and non-linear dynamics.
problem Understanding how recurrence and non-linear dynamics in cortical networks contribute to their function.
method Transformed time-continuous, recurrent dynamics into an effective feed-forward structure of linear and non-linear temporal kernels.
result Optimal time-series classifiers can be built from random reservoir networks, demonstrating significant performance gains.
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.
ASARS integrates temporal dynamics from CF into session-based RNN for better personalized recommendations.
problem Discarding long-term data across sessions in session-based RNNs.
method ASARS framework that combines attentional network and inter-session temporal dynamic model.
result ASARS improves personalized recommendation performance on four real datasets.
A hybrid CNN with shared parameters learns to incorporate recurrent structures.
problem Designing efficient recurrent neural networks.
method Parameter sharing scheme combining CNN and recurrent layers.
result Substantial parameter savings with competitive accuracy.
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.
Recurrent Neural Networks handle sequential data better than traditional networks.
problem Handling temporal context and gradient flow in training RNNs.
method Explains the structure and challenges of RNNs, including training complexities.
result RNNs improve performance in various sequential tasks.
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.
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.
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…
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.
Study mutual info for community detection with covariate and correlated networks.
problem Community detection with covariate and correlated networks.
method Asymptotic upper bound and MMSE matrix heuristic analysis.
result Explicit characterization of combined information effects.
Linear Memory Network separates memory and function in RNNs.
problem Complex transduction problems requiring memory and input-output exploitation.
method Conceptual separation between memory and function, using feedforward and autoencoder components.
result Efficient training and competitive performance on polyphonic music datasets.
SnAp approximates RTRL for online training of sparse recurrent networks.
problem Training large sparse recurrent networks online is computationally expensive.
method Sparse n-step Approximation (SnAp) of the RTRL influence matrix.
result SnAp with n=2 remains tractable for highly sparse networks and outperforms backpropagation through time.
Study on recurrent neural networks' feature selection and memorization using F1B test.
problem Conflict between feature selection and memorization in sequence learning.
method Flagged-1-Bit (F1B) test, four recurrent network models studied analytically and experimentally.
result Conflict can be resolved by gating mechanism or increasing state dimension.
Capsule Networks improve clothing retrieval without landmark info.
problem In-shop clothing retrieval performance improvement.
method Triplet-based Capsule Network architecture with SC and RC blocks.
result Triplet Capsule Networks outperform FashionNet and SOTA architectures.
Generalizes memory and forecasting capacities for nonlinear recurrent networks with dependent inputs.
problem Understanding memory and forecasting capabilities in networks with dependent inputs.
method Formulated bounds for memory and forecasting capacities in terms of network size and input properties.
result Proved that memory capacity for linear recurrent networks with independent inputs is given by the rank of the controllability matrix.
Recurrent-DBN models dynamic relational data with interpretable latent structures.
problem Interpreting dynamic relational data with hidden structures.
method Recurrent Dirichlet Belief Network framework with hierarchical latent structures and efficient inference strategy.
result Recurrent-DBN discovers interpretable latent structures and improves link prediction.
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…
Algorithm discovers dynamic cell structures for better neural network performance.
problem Finding optimal neural network architectures for diverse data samples and time steps.
method Combines recurrent and recursive neural networks to dynamically search for customized cell structures.
result Achieves better prediction accuracy compared to existing models.
Transformers can outperform feedforward and recurrent networks due to dynamic sparsity.
problem Understanding when and why Transformers outperform other neural network architectures.
method Analyzing a sequence-to-sequence data generating model with dynamic sparsity, proving sample complexity differences between feedforward, recurrent, and Transformers.
result Transformers can learn dynamic sparsity models with lower sample complexity than feedforward and recurrent networks.
Lipschitz RNNs improve stability and performance in various tasks.
problem Improving stability and performance of RNNs.
method Introduced a Lipschitz recurrent unit with a linear and Lipschitz nonlinear component for stability analysis.
result Lipschitz RNNs outperform existing units on benchmark tasks.
Reverse engineered RNNs reveal line attractor dynamics for sentiment classification.
problem Understanding how recurrent neural networks solve sequential tasks like sentiment classification.
method Dynamical systems analysis to reverse engineer trained RNNs, identifying fixed points and linearized dynamics.
result Trained RNNs converge to low-dimensional line attractor dynamics, providing interpretable solutions.
Theory explains how recurrent networks remember sequences.
problem Understanding how recurrent networks remember sequences and perform well.
method Mean field theory and random matrix theory applied to RNNs with gating mechanisms.
result Gated RNNs outperform non-gated RNNs in remembering sequences.
Improves sequence modeling with a flow-based recurrent mixture density network.
problem Sequence modeling and sequence-to-sequence mapping applications.
method Generalized recurrent mixture density networks using normalized flow transformations.
result Significantly improved fit to image sequences measured by log-likelihood.
Recurrent Neural Networks (RNNs) with sophisticated units that implement a gating mechanism have emerged as powerful technique for modeling sequential signals such as speech or electroencephalography (EEG). The latter is the focus on this paper. A significant big data resource, known as the TUH EEG Corpus (TUEEG), has …
Large-scale recurrent networks have drawn increasing attention recently because of their capabilities in modeling a large variety of real-world phenomena and physical mechanisms. This paper studies how to identify all authentic connections and estimate system parameters of a recurrent network, given a sequence of node …
Paper improves Native ads CTR prediction using event embeddings and recurrent networks.
problem Hard CTR prediction for Native ads due to lack of direct query intent.
method Proposes a large-scale event embedding scheme and a recurrent neural network model.
result Significantly outperforms baseline and variants in CTR prediction.
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.
ENRNN uses eigenvalue normalization for short-term memory in RNNs.
problem Vanishing/exploding gradient problem and long-term dependency modeling.
method Eigenvalue normalization of recurrent matrix to simulate short-term memory.
result ENRNN outperforms existing RNN variants in experiments.
This work verifies recurrent neural networks using DFA and shows some are robust to adversarial samples.
problem Verifying recurrent neural networks for adversarial robustness.
method Metric for string distance, DFA for oracle, Tomita grammars for testing.
result Some recurrent networks are robust to adversarial samples.
A new memory-efficient sign language translation model reduces weight usage.
problem Memory constraints in real-time sign language translation.
method Variational Bayesian sequence-to-sequence network with Gaussian posterior and Indian Buffet Process prior.
result The proposed model achieves substantial weight compression without compromising performance.
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 …
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.