Study clusters bank customers using LSTM and DTW.
problem Efficiently segmenting bank customers for targeted offers.
method Encoder-decoder LSTM network and Dynamic Time Warping (DTW).
result Hybrid method yields more accurate clusters.
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,742 papers · 148 categories
Trend · papers per month
48 results for “LSTM encoders”
Deep learning models have shown state-of-the-art performance in many inverse reconstruction problems. However, it is not well understood what properties of the latent representation may improve the generalization ability of the network. Furthermore, limited models have been presented for inverse reconstructions over ti…
Status prediction and anomaly detection are two fundamental tasks in automatic IT systems monitoring. In this paper, a joint model Predictor & Anomaly Detector (PAD) is proposed to address these two issues under one framework. In our design, the variational auto-encoder (VAE) and long short-term memory (LSTM) are joine…
In this paper, we propose an interpretable LSTM recurrent neural network, i.e., multi-variable LSTM for time series with exogenous variables. Currently, widely used attention mechanism in recurrent neural networks mostly focuses on the temporal aspect of data and falls short of characterizing variable importance. To th…
In this work, we study abstractive text summarization by exploring different models such as LSTM-encoder-decoder with attention, pointer-generator networks, coverage mechanisms, and transformers. Upon extensive and careful hyperparameter tuning we compare the proposed architectures against each other for the abstractiv…
Bi-directional LSTMs are a powerful tool for text representation. On the other hand, they have been shown to suffer various limitations due to their sequential nature. We investigate an alternative LSTM structure for encoding text, which consists of a parallel state for each word. Recurrent steps are used to perform lo…
Dialogue act (DA) classification has been studied for the past two decades and has several key applications such as workflow automation and conversation analytics. Researchers have used, to address this problem, various traditional machine learning models, and more recently deep neural network models such as hierarchic…
AER combines auto-encoder and LSTM for better time series anomaly detection.
problem Anomaly detection in time series data with limited labeled data and ambiguous definitions.
method AER (Auto-Encoder with Regression) integrates auto-encoder and LSTM for joint predictions and reconstructions.
result AER achieves the highest F1 score across 12 datasets with comparable runtime.
CNN-LSTM models for Multi-Speaker Source Separation using Bayesian Hyper Parameter Optimizationcs.LG
Paper proposes CNN-LSTM model for multi-speaker speech separation.
problem Multi-speaker source separation using deep learning.
method Parallel CNN-LSTM architecture with Bayesian hyperparameter optimization.
result Parallel CNN-LSTM model outperforms LSTM-only and CNN-only models.
HFformer outperforms LSTM in high-frequency trading with multiple signals.
problem Improving high-frequency trading performance using deep learning models.
method Introducing HFformer, a hybrid Transformer model for time series forecasting.
result HFformer achieves higher cumulative PnL than LSTM in backtesting.
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.
The paper presents a neural machine translation system for Wolof.
problem Low-resource conditions for translating French to Wolof.
method Developed a bidirectional LSTM-based encoder-decoder architecture with attention mechanisms.
result Best model achieved a 47% BLEU score for French-Wolof translation.
Improved online AED models with multi-stage training and multi-task learning.
problem Enhance performance of online attention-based encoder-decoder models.
method Three-stage training with character encoder, BPE encoder, and attention decoder; multi-task learning at character and BPE levels; transfer learning from bidirectional encoder.
result 35% and 10% relative improvement over baselines for smaller and bigger models, respectively.
The paper introduces a tensor-based approach to improve neural models' aggregation of structural context.
problem Sub-optimal use of simple aggregation functions in neural models for structured data.
method Tensor-based formulation and Tucker tensor decomposition to control parameter space size.
result Effective regulation of trade-off between expressivity, computational complexity, and generalisation.
LSTM models predict low likelihood of another COVID-19 wave in India.
problem Inaccurate and unreliable COVID-19 infection forecasting models due to data limitations and model complexity.
method Application of LSTM, bidirectional LSTM, and encoder-decoder LSTM models for multi-step infection forecasting.
result Predictions indicate low likelihood of another wave in October and November 2021.
DeepVARMA predicts chemical industry index trends using LSTM and VARMAX models.
problem Forecasting the chemical industry index for economic analysis.
method Combines LSTM and VARMAX models to predict nonstationary series.
result DeepVARMA achieves best prediction accuracy and adaptability.
RTFN extracts robust temporal features for time series analysis.
problem Challenges in extracting sufficient shapelets from time series data.
method Combines temporal feature networks and attentional LSTM networks.
result RTFN outperforms in supervised and unsupervised time series analysis.
We propose a new architecture called Memory-Augmented Encoder-Solver (MAES) that enables transfer learning to solve complex working memory tasks adapted from cognitive psychology. It uses dual recurrent neural network controllers, inside the encoder and solver, respectively, that interface with a shared memory module a…
Improved security of smart contracts by classifying them into four categories.
problem Detecting and classifying vulnerabilities in smart contracts efficiently.
method Used AWD-LSTM for multi-class classification, addressing class imbalance.
result Achieved a weighted average Fbeta score of 90.0%.
Predicting movement of objects while the action of learning agent interacts with the dynamics of the scene still remains a key challenge in robotics. We propose a multi-layer Long Short Term Memory (LSTM) autoendocer network that predicts future frames for a robot navigating in a dynamic environment with moving obstacl…
New RNN model handles long-term dependencies in irregularly-sampled time series.
problem Handling long-term dependencies in irregularly-sampled time series data.
method Designing ODE-LSTMs that separate memory from continuous-time state.
result ODE-LSTMs outperform other RNN-based models on non-uniformly sampled data with long-term dependencies.
Applying neural-networks on Question Answering has gained increasing popularity in recent years. In this paper, I implemented a model with Bi-directional attention flow layer, connected with a Multi-layer LSTM encoder, connected with one start-index decoder and one conditioning end-index decoder. I introduce a new end-…
LD-EnSF speeds up data assimilation with sparse observations.
problem Efficiently assimilate sparse and noisy data into complex dynamical systems.
method LD-EnSF uses latent dynamics networks and history-aware LSTM encoders to process sparse observations without full-space simulations.
result Achieves significant speedups over existing methods while maintaining high accuracy.
Predicting Aircraft Trajectories: A Deep Generative Convolutional Recurrent Neural Networks Approachcs.LG
Reliable 4D aircraft trajectory prediction, whether in a real-time setting or for analysis of counterfactuals, is important to the efficiency of the aviation system. Toward this end, we first propose a highly generalizable efficient tree-based matching algorithm to construct image-like feature maps from high-fidelity m…
PT network optimizes asset weights without forecasting returns.
problem Traditional asset allocation methods are error-prone and limit portfolio performance.
method PT network uses attention mechanisms to directly optimize Sharpe ratio.
result PT outperforms other algorithms in risk-adjusted performance.
Recurrent neural networks have become ubiquitous in computing representations of sequential data, especially textual data in natural language processing. In particular, Bidirectional LSTMs are at the heart of several neural models achieving state-of-the-art performance in a wide variety of tasks in NLP. However, BiLSTM…
LSTMs promise much to financial time-series analysis, temporal and cross-sectional inference, but we find that they do not deliver in a real-world financial management task. We examine an alternative called Continual Learning (CL), a memory-augmented approach, which can provide transparent explanations, i.e. which memo…
Image denoising is always a challenging task in the field of computer vision and image processing. In this paper, we have proposed an encoder-decoder model with direct attention, which is capable of denoising and reconstruct highly corrupted images. Our model consists of an encoder and a decoder, where the encoder is a…
CTLNet predicts Shanghai Composite Index with improved accuracy.
problem Predicting Shanghai Composite Index for investors and researchers.
method Proposes CNN-Transformer-LSTM Networks (CTLNet) for multivariate time series forecasting.
result CTLNet outperforms state-of-the-art baselines in Shanghai Composite Index prediction.
Stable long-term predictions for fluid flows using neural networks.
problem Predicting complex dynamics of fluid flows with high temporal stability.
method End-to-end trained neural network architecture combining CNN for spatial compression and LSTM for temporal prediction.
result Novel latent space subdivision (LSS) allows stable and controllable long-term predictions.
We describe a simple neural language model that relies only on character-level inputs. Predictions are still made at the word-level. Our model employs a convolutional neural network (CNN) and a highway network over characters, whose output is given to a long short-term memory (LSTM) recurrent neural network language mo…
A minimal RNN model learns to generate new characters from a single example.
problem Learning efficiency and compositional ability in AI.
method Minimal RNN model with one-shot inference mechanism.
result The model can recombine previously learned substructures to generate new characters.
A new method approximates deep neural networks using Kalman Filters.
problem Approximating deep neural networks with limited data.
method Matrix Ensemble Kalman Filter-based multi-arm ANN (MEnKF-ANN).
result MEnKF-ANN can adequately approximate LSTM networks and provide uncertainty estimates.
The Linear Attention Recurrent Neural Network (LARNN) is a recurrent attention module derived from the Long Short-Term Memory (LSTM) cell and ideas from the consciousness Recurrent Neural Network (RNN). Yes, it LARNNs. The LARNN uses attention on its past cell state values for a limited window size . The formulas ar…
Majority of semantic segmentation algorithms operate on a single frame even in the case of videos. In this work, the goal is to exploit temporal information within the algorithm model for leveraging motion cues and temporal consistency. We propose two simple high-level architectures based on Recurrent FCN (RFCN) and Mu…
New method for Transformer models to encode position information without sequential bias.
problem Lack of flexible and learnable position encoding for Transformer models.
method Continuous dynamical model to learn position encoding.
result Consistent improvements over baselines in various NLP tasks.
Deep model forecasts correlated multivariate time series.
problem Forecasting correlated multivariate time series.
method Deep learning structural model using CNN-LSTM architecture.
result Model outperforms state-of-the-art methods in various time series data sets.
Anomaly detection is a classical but worthwhile problem, and many deep learning-based anomaly detection algorithms have been proposed, which can usually achieve better detection results than traditional methods. In view of reconstruct ability of the model and the calculation of anomaly score, this paper proposes a time…
Long short-term memory (LSTM) is normally used in recurrent neural network (RNN) as basic recurrent unit. However,conventional LSTM assumes that the state at current time step depends on previous time step. This assumption constraints the time dependency modeling capability. In this study, we propose a new variation of…
SummaryNet automates video summarisation using deep learning.
problem Creating informative video summaries from videos.
method Two-stream convolutional network for spatial and temporal features, encoder-decoder model for salient features, sigmoid regression with LSTM for frame probability.
result SummaryNet achieves comparable or better results than state-of-the-art methods on benchmark datasets.
Long Short-Term Memory (LSTM) is a well-known method used widely on sequence learning and time series prediction. In this paper we deployed stacked LSTM model in an application of weather forecasting. We propose a 2-layer spatio-temporal stacked LSTM model which consists of independent LSTM models per location in the f…
We propose a generalization of neural network sequence models. Instead of predicting one symbol at a time, our multi-scale model makes predictions over multiple, potentially overlapping multi-symbol tokens. A variation of the byte-pair encoding (BPE) compression algorithm is used to learn the dictionary of tokens that …
Neural language modeling (LM) has led to significant improvements in several applications, including Automatic Speech Recognition. However, they typically require large amounts of training data, which is not available for many domains and languages. In this study, we propose a multilingual neural language model archite…
In this paper we propose a deep neural network model with an encoder-decoder architecture that translates images of math formulas into their LaTeX markup sequences. The encoder is a convolutional neural network (CNN) that transforms images into a group of feature maps. To better capture the spatial relationships of mat…
We consider the problem of active feature acquisition, where we sequentially select the subset of features in order to achieve the maximum prediction performance in the most cost-effective way. In this work, we formulate this active feature acquisition problem as a reinforcement learning problem, and provide a novel fr…
Neural-PDE learns PDEs from data using LSTM, outperforming traditional methods.
problem Solving time-dependent PDEs numerically is challenging.
method Bidirectional LSTM encoder to learn governing rules from data.
result Neural-PDE efficiently predicts PDE dynamics with minimal parameters.
MC-LSTM extends LSTM to conserve mass in neural networks.
problem Conservation laws in real-world systems.
method Extending LSTM's inductive bias to conserve mass.
result MC-LSTM sets new state-of-the-art for predicting peak flows.
The problem of video frame prediction has received much interest due to its relevance to many computer vision applications such as autonomous vehicles or robotics. Supervised methods for video frame prediction rely on labeled data, which may not always be available. In this paper, we provide a novel unsupervised deep-l…