A novel sequence-to-sequence model predicts missing sensor data.
problem Missing sensor data in sequences.
method Formulated a novel sequence-to-sequence model using forward and backward RNNs.
result The model produces the lowest errors in 12% more cases than the current state-of-the-art.
Deep generative models have been successfully used to learn representations for high-dimensional discrete spaces by representing discrete objects as sequences and employing powerful sequence-based deep models. Unfortunately, these sequence-based models often produce invalid sequences: sequences which do not represent a…
Paper defines and evaluates attention mechanisms for sequence to sequence tasks.
problem Improving sequence to sequence mapping tasks.
method Mathematical definition and evaluation of attention mechanisms in sequence to sequence models.
result Models using greater attention perform better and converge faster.
Unified approach for generating sequences from undirected models.
problem Generating sequences directly from undirected models like BERT.
method Generalized model of sequence generation unifying decoding in directed and undirected models.
result Adapted decoding algorithms for undirected models achieve competitive results.
Enhances sequence memory capacity in neural networks.
problem Limited sequence capacity in Hopfield-like neural networks.
method Introducing a nonlinear interaction term and a generalized pseudoinverse rule.
result Significantly increased sequence capacity with novel scaling laws.
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.
A new mechanism for GANs improves text generation by evaluating sub-sequences.
problem Exposure bias and mode collapse in GANs for text generation.
method Segmenting the sequence into sub-sequences and evaluating them individually.
result Significant improvement in text generation models on benchmark data.
Transformers can approximate any sequence-to-sequence function, surprising given their complexity.
problem Understanding the expressive power of Transformer models for sequence-to-sequence functions.
method Established that Transformers are universal approximators of continuous permutation equivariant sequence-to-sequence functions with compact support, and extended this to arbitrary functions using positional encodings.
result Transformers are universal approximators of arbitrary continuous sequence-to-sequence functions on a compact domain.
A convolutional sequence to sequence non-intrusive load monitoring model is proposed in this paper. Gated linear unit convolutional layers are used to extract information from the sequences of aggregate electricity consumption. Residual blocks are also introduced to refine the output of the neural network. The partiall…
Deep learning models optimize protein sequences.
problem Optimizing protein properties through sequence design.
method Deep generative models guided by machine learning.
result Improved protein sequence generation from prior knowledge.
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.
The availability of large amounts of time series data, paired with the performance of deep-learning algorithms on a broad class of problems, has recently led to significant interest in the use of sequence-to-sequence models for time series forecasting. We provide the first theoretical analysis of this time series forec…
Predicts node sequences in graphs using multi-order network models.
problem Predicting sequences of node traversals in graphs.
method Combines multiple higher-order network models into a multi-order model, fitting and selecting the optimal maximum order.
result Outperforms state-of-the-art algorithms for next-element and full sequence prediction.
Deep learning techniques have been hugely successful for traditional supervised and unsupervised machine learning problems. In large part, these techniques solve continuous optimization problems. Recently however, discrete generative deep learning models have been successfully used to efficiently search high-dimensiona…
This work compresses sequences by treating them as continuous-time processes, enabling efficient discretization.
problem Efficient compression of sequences, especially with deep learning models that scale with sequence length.
method Treat sequences as continuous-time processes, learn efficient discretization, and decode at different time intervals.
result Automatic bit rate reductions in video and motion capture sequences using learned discretization.
Generative models have long been the dominant approach for speech recognition. The success of these models however relies on the use of sophisticated recipes and complicated machinery that is not easily accessible to non-practitioners. Recent innovations in Deep Learning have given rise to an alternative - discriminati…
Sequence-to-Sequence (seq2seq) modeling has rapidly become an important general-purpose NLP tool that has proven effective for many text-generation and sequence-labeling tasks. Seq2seq builds on deep neural language modeling and inherits its remarkable accuracy in estimating local, next-word distributions. In this work…
Study SGD dynamics in sequence models, revealing training phases and influence of sequence length.
problem Understanding SGD in sequence models like attention networks.
method Derived closed-form population loss and analyzed SGD dynamics for SSI models.
result Two distinct training phases: escape from uninformative initialization and alignment with target subspace.
ProGen models protein sequences for synthetic biology.
problem Generating proteins without structural annotations.
method Trained a 1.2B-parameter language model on 280M protein sequences.
result ProGen generates proteins with fine-grained control and accuracy.
HARMLESS meta-learning method models short event sequences with relational information.
problem Learning heterogeneous point process models from short event sequence data.
method Hierarchical Bayesian mixture Hawkes process model with stochastic variational meta expectation maximization.
result HARMLESS outperforms existing methods in predicting future events.
Study Thompson Sampling in adversarial bit prediction, finding regret bounds and optimal sequences.
problem Adversarial bit prediction with varying error weights.
method Thompson Sampling, analyzing sequences with largest and smallest regret.
result Regret bounds for adversarial bit prediction sequences, including optimal and worst-case scenarios.
nTreeClus clusters categorical sequences using tree-based learners and k-mers.
problem Challenges in clustering categorical and sequential data.
method nTreeClus uses Tree-based Learners, k-mers, and autoregressive models for categorical time series.
result nTreeClus outperformed baseline methods in various validation metrics.
Bayesian context trees capture complex dependencies in categorical sequences.
problem Complex, long-range dependencies in categorical sequences are not well captured by simple models.
method Parsimonious Bayesian context trees with model-based agglomerative clustering for efficient inference.
result The proposed framework outperforms existing models on real-world data.
Develops a new point process model for detecting neural spike sequences.
problem Detecting sparse sequences of neural spikes in high-dimensional spike trains.
method A point process model that represents sequence occurrences as marked events in continuous time, with learnable time warping parameters.
result Demonstrates improved detection and modeling of neural spike sequences.
New techniques improve channel prediction in noisy wireless systems.
problem Predicting channels in wireless communication systems from noisy observations.
method Adapted sequence-to-sequence models and transformers with reverse positional encoding and reversed encoder outputs.
result Improved robustness and relationship capture in channel prediction models.
This research explores various sampling methods and probability distributions for hard alignment in sequence-to-sequence TTS synthesis.
problem Improving alignment accuracy in sequence-to-sequence text-to-speech synthesis.
method Investigated various sampling methods (greedy, beam, random) and probability distributions (Bernoulli, Concrete) for hard alignment.
result Deterministic search is more preferable than stochastic search for natural alignment transition.
OptiGAN uses GAN and RL to optimize sequence generation for specific goals.
problem Challenging in sequence generation tasks to generate sequences with specific desired goals.
method Integrates GAN and RL to optimize desired goal scores using policy gradients.
result Achieves higher desired scores in text and real-valued sequence generation.
A new loss function speeds up sequence-to-sequence models for continuous outputs.
problem Slow and memory-intensive softmax layer limits vocabulary size and translation quality.
method Proposes a probabilistic loss and continuous embedding layer training/inference procedure.
result Models achieve up to 2.5x speed-up in training time with similar translation quality.
The paper extends sequences while preserving statistical properties using a mixture model.
problem Extending sequences while retaining their statistical properties.
method Auto-regressive Sequence Extension Mixture Model (SEMM) using deep learning.
result The mixture model outperforms traditional neural networks in sequence extension with statistical property retention.
Seq2seq models predict complex multi-physics systems' time evolution.
problem Predicting the time-evolution of complex multi-physics systems.
method Sequence-to-sequence models applied to multi-physics simulations.
result Seq2seq models accurately emulate complex systems and predict their evolution.
Compressive Transformer learns long-range sequences by compressing past memories.
problem Learning long-range sequences in language and speech models.
method Compressive Transformer compresses past memories for efficient long-range sequence learning.
result State-of-the-art performance on language and speech benchmarks.
FIGARO generates symbolic music with fine-grained control.
problem Minimal control over generated music sequences.
method Description-to-sequence task, learning conditional distribution of sequences given high-level descriptions.
result State-of-the-art controllable symbolic music generation.
Study reveals how machine translation models can leak data privacy.
problem Detecting if a specific data sample was used to train machine translation models.
method Defined membership inference problem for sequence-to-sequence models, tested on machine translation models.
result Machine translation models can leak private information about training data.
A new method optimizes neural sequence models for better task performance.
problem Training neural sequence models with maximum likelihood estimation ignores task losses.
method Maximum likelihood guided parameter search (MGS) in the parameter space.
result MGS optimizes sequence-level losses, reducing repetition and non-termination.
Sequence models quantify uncertainty over latent concepts.
problem Quantifying uncertainty in latent environments.
method Exchangeable sequence models, equivalent to empirical Bayes and posterior inference.
result Sequence prediction loss controls uncertainty quantification.
k-Nearest Neighbors is one of the most fundamental but effective classification models. In this paper, we propose two families of models built on a sequence to sequence model and a memory network model to mimic the k-Nearest Neighbors model, which generate a sequence of labels, a sequence of out-of-sample feature vecto…
New model controls memory in seq2seq tasks, revealing learning regimes.
problem Understanding memory in seq2seq tasks using neural networks.
method Introducing a stochastic switching-Ornstein-Uhlenbeck (SSOU) model to control memory and a measure of non-Markovianity.
result Two learning regimes emerge from the interplay of time scales in the SSOU process.
We present a recurrent encoder-decoder deep neural network architecture that directly translates speech in one language into text in another. The model does not explicitly transcribe the speech into text in the source language, nor does it require supervision from the ground truth source language transcription during t…
Investigates neural TTS systems for Japanese and English.
problem Improving neural TTS systems for high-quality speech synthesis.
method Comparative study of neural sequence-to-sequence TTS vs. DNN pipeline TTS, varying model architecture, parameter size, and language.
result A neural sequence-to-sequence TTS system requires sufficient model parameters and a powerful encoder for high-quality speech synthesis.
Paper tackles adaptive deletion of data points from trained models.
problem Adaptive deletion of data points from trained models.
method Reduction from adaptive to non-adaptive deletion guarantees using differential privacy and max information.
result Strong provable deletion guarantees for adaptive deletion sequences.
ATS2S model predicts RUL of industrial equipment using attention mechanism.
problem Accurate estimation of RUL for industrial equipment to improve maintenance schedules and reduce costs.
method ATS2S model that optimizes reconstruction and RUL prediction losses, uses attention mechanism, and integrates encoder and decoder features.
result ATS2S model achieves superior performance over 13 state-of-the-art methods on four real datasets.
Lingvo is a flexible framework for deep learning sequence models.
problem Sequence-to-sequence modeling challenges in deep learning.
method Modular, scalable, and customizable Tensorflow framework.
result Supports distributed training and quantized inference.
Attention forcing improves sequence-to-sequence model training stability.
problem Training auto-regressive sequence-to-sequence models with attention mechanism is challenging.
method Attention forcing guides the model with generated output history and reference attention.
result Attention forcing trains models to recover from mistakes without requiring a schedule or classifier.
MTDS improves sequence generation adaptability via latent code control.
problem Lack of adaptability in sequence generation models like RNNs.
method Hierarchical multi-task dynamical systems (MTDS) with latent code control.
result MTDS enables style transfer, interpolation, and morphing in generated sequences.
A framework infers causal direction from symbolic sequences using compression measures.
problem Inferring causal direction from two observed discrete symbolic sequences.
method Lossless compressors for inferring context-free grammars (CFGs) and quantifying compression extent.
result Grammar inferred from one sequence better compresses the other sequence, indicating causal direction.
This paper studies mutual information in sequence models and finds Transformers excel in capturing long-range dependencies.
problem Understanding the expressive power of sequence models in capturing temporal dependencies.
method Theoretical and empirical analysis of linear and nonlinear RNNs, including Transformers.
result Transformers can capture long-range mutual information more efficiently than RNNs.
Existence of an infinite sequence of harmonic maps between spheres of certain dimensions was proven by Bizon and Chmaj. This sequence shares many features of the Bartnik-McKinnon sequence of solutions to the Einstein-Yang-Mills equations as well as sequences of solutions that have arisen in other physical models. We ap…
Develops a hybrid model for text summarization.
problem Summarizing long text sequences concisely.
method Extends sequence encoders with a graph component to handle long-distance relationships in text.
result Hybrid models outperform pure sequence or graph models on summarization tasks.