Bidirectional bounds stabilize training of energy-based models.
problem Training energy-based models is difficult and prone to instability.
method Propose bidirectional bounds linking to gradient penalty and Jacobi-determinant estimator.
result Significant stabilization and high-quality density estimation achieved.
BiCoGAN improves cGANs by disentangling latent and auxiliary variables.
problem Improving disentanglement of latent and auxiliary variables in cGANs.
method BiCoGAN uses bidirectional training with extrinsic factor loss and dynamically-tuned importance weight.
result BiCoGAN encodes auxiliary variables more accurately and disentangles latent and auxiliary variables effectively.
Proposes FBFAN to defend against adversarial attacks by learning semantic features.
problem Vulnerability of deep neural networks to adversarial attacks.
method Featurized Bidirectional Generative Adversarial Networks (FBGAN) that learns semantic features and filters non-semantic perturbations.
result FBGAN effectively reconstructs adversarial data to denoised data, improving classifier performance.
Paper proposes using LSTM for LSH-based sequence alignment.
problem Sequence alignment using deep learning models.
method Deep bidirectional LSTM for feature learning and LSH-based sequence alignment.
result Higher accuracy achieved with LSTM-based model.
Bidirectional LSTM predicts seizures with 84% accuracy.
problem Predicting seizures for epilepsy patients to prevent drug side effects.
method Trained EEG data from canines on a double Bidirectional LSTM layer.
result AUC of 0.84 on test dataset, significantly better than SVM and GRU networks.
Bidirectional diffusion models predict their own rollout errors without ground truth.
problem Long rollouts accumulate error in autoregressive models, lacking a reliable test-time error signal.
method Train a bidirectional latent diffusion model that steps forward or backward, measuring discrepancies to estimate error.
result Bidirectional consistency Ci ranks rollout error and predicts magnitude with high accuracy. New method for bidirectional generative modeling using adversarial gradient estimation.
problem Bidirectional generative modeling with various f-divergences. method Adversarial gradient estimation for f-divergence optimization. result Similar algorithms for different f-divergences with varying scaling. Extracts parallel sentences for machine translation.
problem Data sparsity in multilingual natural language processing.
method Bidirectional recurrent neural network approach.
result Significant improvements in machine translation performance.
BiHRNN predicts inflation by leveraging hierarchical structure and bidirectional RNNs.
problem Accurate inflation forecasting is challenging due to dynamic factors and the layered structure of the Consumer Price Index.
method Bi-directional Hierarchical Recurrent Neural Network (BiHRNN) model that uses bidirectional information flow between levels and informative constraints on RNN parameters.
result BiHRNN significantly outperforms traditional RNN models in forecasting accuracy.
Bidirectional learning improves neural network robustness to noise and attacks.
problem Improving neural network robustness to adversarial and static noise.
method Bidirectional learning (BL) techniques using error propagation and hybrid adversarial networks (HAN).
result Both methods improve robustness and accuracy, with HAN showing state-of-the-art performance.
Regularized SB process speeds up generative modeling.
problem Slow sampling and training times in SB-based models.
method Regularization terms to reduce timesteps and training time.
result Faster sampling speed for generative modeling.
Delayed-RNN approximates stacked and bidirectional RNNs.
problem Improving RNN expressiveness and representational capacity.
method Weight-constrained delayed-RNN, equivalent to stacked-RNNs, with partial acausality.
result Delayed-RNN can approximate stacked and bidirectional RNNs, outperforming them in some tasks.
PLUS pre-trains protein sequences with structural info, improving performance.
problem Lack of labeled protein sequences for training models.
method PLUS combines masked language modeling with same-family prediction for pre-training.
result PLUS-RNN outperforms other models in protein biology tasks.
Semi-supervised learning using BiGAN with triplet loss.
problem Training GANs with limited labeled data.
method BiGAN with triplet loss for semi-supervised learning.
result BiGAN latent space features improve classification and retrieval.
Paper improves video feature learning for better downstream tasks.
problem Improving video feature learning for better performance on downstream tasks.
method Self-supervised learning approach using contrastive bidirectional transformer, extending BERT for real-valued feature vectors.
result Significantly improved performance on video classification, captioning, and segmentation tasks.
We improve GANs by enforcing reproducibility and using non-uniform sampling.
problem Overrepresentation of certain samples in GANs' marginal log-likelihood.
method Enforce reproducibility through matching empirical distribution to prior, use non-uniform sampling for mini-batch selection.
result Improved quality and variety in generated samples, validated on CIFAR10, Fashion MNIST, and CelebA.
Bidirectional attention is shown to be equivalent to a continuous bag of words model with mixture-of-experts.
problem Understanding the statistical underpinnings of bidirectional attention.
method Exploring bidirectional attention as a mixture-of-experts model and reparameterizing it.
result Bidirectional attention can be viewed as a continuous bag of words model with mixture-of-experts weights.
Bidirectional sequence generation improves performance in conversational tasks.
problem Neural sequence generation typically considers only past tokens, limiting performance.
method Introduced placeholder tokens that can consider both past and future tokens in sequence generation.
result Bidirectional model outperforms competitive baselines on conversational tasks.
Bidirectional VAE reduces parameters and improves image tasks.
problem Improving image reconstruction, classification, interpolation, and generation.
method Uses a single neural network for both encoding and decoding in both forward and backward directions.
result Bidirectional VAEs reduce parameters by almost 50% and slightly outperform unidirectional VAEs.
Unified approach to stabilize adversarial learning for joint distribution matching.
problem Non-identifiability issues in bidirectional adversarial training.
method Unified framework of adversarial and non-adversarial approaches, stabilizing learning.
result Stabilized learning of unsupervised and semi-supervised bidirectional adversarial methods.
Sharp error bounds derived for bidirectional GANs without restrictive assumptions.
problem Estimating the error of bidirectional GANs under various conditions.
method Dudley distance, neural network functions, decomposition of IPM.
result Nearly sharp bounds for bidirectional GAN estimation error.
New bidirectional model predicts magnetohydrodynamics fields and estimates uncertainty.
problem Predicting multiple fields in magnetohydrodynamics with uncertainty.
method Bidirectional autoregressive latent diffusion approach.
result Model can estimate uncertainty without ground truth using self-supervised consistency.
A single BLSTM network tackles ambiguous words in text data.
problem Ambiguity in text data, especially in technical domains.
method Proposes a single Bidirectional LSTM network for all ambiguous words.
result Comparable performance to top WSD algorithms on SensEval-3 benchmark.
New method estimates bidirectional causal effects in large-scale systems.
problem Estimating bidirectional causal effects in systems with mutual dependence and heteroskedasticity.
method Heteroskedasticity-based identification with online kernel learning and random Fourier features.
result Superior accuracy and stability compared to single equation and polynomial approximations.
A new deep learning method for energy disaggregation.
problem Energy disaggregation or non-intrusive load monitoring (NILM) to identify individual appliance power usage.
method Sequence to Point Learning based on Bidirectional Dilated Residual Network (BRDN).
result Our method outperforms state-of-the-art approaches in all appliances on REDD and UK-DALE datasets.
cvHM framework speeds up GP inference for neural spike train analysis.
problem Scalability issue in approximate inference for latent GP models.
method cvHM framework using Hida-Matérn kernels and conjugate computation variational inference (CVI).
result Linear time inference for latent neural trajectories.
We propose a new cognitive framework for option price modelling, using quantum neural computation formalism. Briefly, when we apply a classical nonlinear neural-network learning to a linear quantum Schrödinger equation, as a result we get a nonlinear Schrödinger equation (NLS), performing as a quantum stochastic filter…
TimeVQVAE uses VQ for better time series generation.
problem Training GANs and RNNs for time series generation have limitations.
method Vector quantization with bidirectional transformer priors in time-frequency domains.
result Generates high-quality synthetic signals with better temporal consistency.
Paper proposes BMPO to optimize policies using bidirectional models.
problem Model-based reinforcement learning's reliance on forward model accuracy.
method Develops BMPO using both forward and backward models for policy optimization.
result BMPO outperforms state-of-the-art methods in sample efficiency and asymptotic performance.
SPID-GAN learns bidirectional mappings in subsurface models.
problem Challenges in identifying and approximating causal structures in high-dimensional parameter spaces.
method Generative adversarial networks (GANs) for learning cross-domain mappings.
result SPID-GAN achieves satisfactory performance in identifying bidirectional state-parameter mappings.
Sketch-BERT learns vector sketches using BERT-like self-supervised learning.
problem Lack of effective vector sketch representation for recognition and retrieval tasks.
method Generalized BERT to sketch domain with novel embedding networks and self-supervised sketch gestalt learning.
result Improved performance on sketch recognition, retrieval, and gestalt tasks.
Bi-Mamba model predicts diffusion coefficients and exponents from short data.
problem Characterizing anomalous diffusion in complex systems.
method Bidirectional state-space deep learning architecture.
result Efficient inference of diffusion coefficient and exponent from short trajectories.
NRWS improves training of SBNs and HMs using natural gradient.
problem Training Sigmoid Belief Networks and Helmholtz Machines efficiently.
method Exploits block-diagonal structure of Fisher Information Matrices to use natural gradient.
result NRWS and NBiHM achieve better log-likelihood and faster convergence.
Paper improves communication in distributed optimization, reducing worker-to-server data exchanges.
problem Efficiency in server-to-worker communication in distributed optimization.
method MARINA-P, a novel downlink compression method using correlated compressors; M3, combining MARINA-P with uplink compression.
result MARINA-P achieves provably superior server-to-worker communication complexity with increasing number of workers.
Improved sentence modeling using Suffix Bidirectional LSTM.
problem Sequential bias in BiLSTMs limits long-range dependencies.
method Encodes each suffix and prefix of a sequence in both forward and reverse directions.
result SuBiLSTM improves performance in various NLP tasks.
Global convergence of multilayer neural networks proven for any depth.
problem Global convergence of multilayer neural networks in the mean field regime.
method Mean field limit framework, neuronal embedding, bidirectional diversity condition.
result Global convergence for multilayer networks of any depths, including correlated initializations.
DBGAN learns graph node representations by balancing distribution consistency.
problem Graph representation learning overfits due to ignoring data distribution.
method DBGAN uses a structure-aware prior distribution and bidirectional adversarial learning.
result DBGAN achieves better trade-off between robustness and dimensionality.
U-Det improves lung nodule segmentation in CT images.
problem Challenging shapes and surroundings of lung nodules in CT images.
method End-to-end deep learning with Bi-FPN, Mish activation, and class weights.
result U-Det achieves 82.82% Dice similarity coefficient, comparable to human experts.
Artemis framework improves distributed learning with bidirectional compression and partial participation.
problem Learning in distributed or federated settings with communication constraints and device partial participation.
method Artemis framework using bidirectional compression, memory mechanism, and Polyak-Ruppert averaging.
result Fast rates of convergence (linear up to a threshold) under weak assumptions on stochastic gradients.
Improves text-to-image generation with bidirectional capabilities.
problem Generating realistic images from text descriptions.
method Integrates text and image modalities using MMVR architecture with n-gram cost function and multiple sentences.
result Significant improvement in image quality over existing methods (over 20%).
BIN and CBN models infer health variables from symptoms and signals.
problem Inferring health variables from symptoms and signals.
method Bidirectional inference networks (BIN) and composite BIN (CBIN).
result CBIN achieves state-of-the-art performance and better accuracy.
Proposes MRNet-Product2Vec for product embeddings in e-commerce.
problem Creating dense, low-dimensional product embeddings for diverse tasks.
method Discriminative Multi-task Bidirectional Recurrent Neural Network (RNN) with Bidirectional RNN input and fifteen product labels output.
result Product embeddings perform almost as well as TF-IDF but with less dimensionality.
Study compares BERT with other sentiment analysis models.
problem Comparing sentiment analysis techniques.
method Used four models: Sent WordNet, logistic regression, LSTM, and BERT on IMDB movie reviews.
result BERT outperformed other models in sentiment classification.
Hybrid model combines RNNs, encoders-decoders, and Transformers for sequence tasks.
problem Sequence labelling tasks
method Combination of bidirectional RNNs, encoder-decoder, and Transformer models
result Results are close to state-of-the-art and better for some tasks
Flashback Learning balances model stability and plasticity in continual learning.
problem Balancing model stability and plasticity in continual learning.
method Flashback Learning (FL) uses a bidirectional regularization approach to balance stability and plasticity.
result FL improves model accuracy by up to 4.91% in Class-Incremental and 3.51% in Task-Incremental settings.
Improved BERT model with latent persona and topic variables.
problem Improving BERT's domain-specific utility while maintaining generalization.
method Combining BERT with Universal Transformer, adding latent persona and topic variables.
result Pre-trained model for social texts outperforms baseline.
Paper analyzes and compares ELF algorithms for federated learning.
problem Improving efficiency and privacy in federated learning.
method Proposes P-ELF, D-ELF, and B-ELF algorithms with primal, dual, and bidirectional compression.
result Provides non-asymptotic convergence guarantees under Log-Sobolev inequality.
We present here a new model and algorithm which performs an efficient Natural gradient descent for Multilayer Perceptrons. Natural gradient descent was originally proposed from a point of view of information geometry, and it performs the steepest descent updates on manifolds in a Riemannian space. In particular, we ext…