Structural-Jump-LSTM speeds up reading by skipping and jumping text.
problem Sequential inference in RNNs makes reading time linearly dependent on input length.
method Introduces a novel LSTM model with agents for skipping and jumping text.
result Structural-Jump-LSTM achieves best FLOP reduction and maintains or improves accuracy.
New approach speeds up DNA sequence alignment.
problem Efficiently estimating alignment scores for large sets of reads.
method Rank-one crowdsourcing models and multi-armed bandit algorithm.
result Adaptive algorithm identifies pairs with large alignment scores.
Improves text-to-speech speed by interleaving character reading and audio synthesis.
problem Latency in text-to-speech models limits their use in time-sensitive tasks.
method Reinforcement learning to train an agent to choose the order of character reading and audio synthesis.
result The proposed method successfully balances latency and audio quality.
New metrics predict human sentence comprehension across languages.
problem Predicting human sentence comprehension using computational models.
method Developed sentence-level metrics using multilingual large language models.
result Achieved high accuracy in predicting human sentence reading speeds.
A novel conLSH algorithm improves alignment of noisy SMRT reads.
problem High error probability in SMRT sequencing data.
method Context-based Locality Sensitive Hashing (conLSH) for efficient alignment.
result Comprehensive improvement in speed and memory requirements compared to rHAT.
Neural network optimizes learning sequence for reading words.
problem Children struggle with learning to read words due to inconsistent spelling-sound correspondences.
method Used a neural network to structure learning trials to optimize generalization accuracy.
result Significant improvement in generalization accuracy compared to random or frequency-based sequences.
Recent empirical results on long-term dependency tasks have shown that neural networks augmented with an external memory can learn the long-term dependency tasks more easily and achieve better generalization than vanilla recurrent neural networks (RNN). We suggest that memory augmented neural networks can reduce the ef…
Neural model detects DD risk in 5-year-olds, predicting 2 years ahead.
problem Early detection of developmental dyslexia for preventive teaching.
method Mixed neural model using auto-encoder and ordinal regression.
result System predicts DD risk 2 years before phonological processing is assessed.
CopyCAT attacks neural policies by manipulating observations, not states.
problem Adversarial attacks on neural reinforcement learning agents.
method CopyCAT is a targeted attack that lures agents into following outsider policies.
result CopyCAT is effective in a read-only setting where adversaries can only manipulate observations.
Proposes a graph neural network for personalized news recommendation.
problem Data sparsity in news recommendation systems.
method Heterogeneous graph model + Graph Neural Networks + LSTM attention mechanism.
result Significantly outperforms state-of-the-art methods on news recommendation datasets.
Loss Data Analytics is an interactive, online, freely available text. The idea behind the name Loss Data Analytics is to integrate classical loss data models from applied probability with modern analytic tools. In particular, we seek to recognize that big data (including social media and usage based insurance) are here…
Structured pruning method reduces RNN sizes and speeds up inference.
problem Large RNN models are hard to deploy on edge devices.
method Structured pruning through neuron selection, minimizing L0 norm of weight matrix.
result Nearly 20x speedup achieved without performance loss.
Neural models often incorrectly predict the same answer to subtly changed questions, even when they should not.
problem Neural models' oversensitivity to adversarial question changes.
method Formulated a noisy adversarial attack to identify and exploit undersensitivity, tested with data augmentation and adversarial training.
result Undersensitivity can be exploited to mislead models, and addressing it improves model performance and robustness.
Paper uses genome Markov structure for outlier detection and read classification.
problem Identifying outliers and classifying reads in genome databases.
method Applying second-order Markov models to triplet base distributions.
result Improved accuracy in outlier identification and read classification.
Semi-supervised deep learning detects problematic reads for genome assembly.
problem De novo genome assembly is hindered by specific types of reads.
method Analysis of coverage graphs converted to 1D-signals using semi-supervised deep learning models.
result Semi-supervised deep learning models can detect problematic reads with minimal labeled data.
Memory networks are neural networks with an explicit memory component that can be both read and written to by the network. The memory is often addressed in a soft way using a softmax function, making end-to-end training with backpropagation possible. However, this is not computationally scalable for applications which …
With an aging and growing population, the number of women requiring either screening or symptomatic mammograms is increasing. To reduce the number of mammograms that need to be read by a radiologist while keeping the diagnostic accuracy the same or better than current clinical practice, we develop Man and Machine Mammo…
A novel observer-based method detects and recovers anomalies in CAV sensor readings.
problem Improving safety and security in connected and automated vehicles.
method Combines model-based signal filtering and anomaly detection methods using AEKF and OCSVM.
result The proposed method achieves better anomaly detection performance compared to traditional methods.
Dataset for measuring reading levels in India's children.
problem Measuring reading levels in India's vast population.
method Developed ASER dataset with 5,301 subjects in Hindi, Marathi, and English.
result Achieved 86% accuracy in English language classification.
TM-CNN predicts lane-level traffic speeds considering volume impact.
problem Aggregated lane-level traffic speed prediction and volume impact.
method Two-stream multi-channel CNN, data conversion, two-stream deep neural network, loss function.
result TM-CNN outperforms existing models in multi-lane traffic speed prediction.
Model predicts traffic incident duration and identifies key features.
problem Predict traffic incident duration and identify critical features.
method Multi-task learning framework with sparsity optimization and ADMM algorithm.
result Model predicts incident duration and identifies key features effectively.
Proposes CSRN for better news recommendation by integrating RNN and UserCF.
problem Lack of societal influence in news recommendation.
method Integrates RNN-based sequential recommendation and UserCF, using a directed co-reading network.
result Significantly outperforms state-of-the-art approaches in news recommendation.
Paper tackles non-convex constrained DRO with a stochastic algorithm for large-scale applications.
problem Training robust models against data distribution shifts with non-convex loss functions.
method Developed a stochastic algorithm for non-convex constrained DRO with a complexity independent of dataset size.
result Algorithm finds ε-stationary points with computational complexity of O(ε^(-3k_*-5)) for general Cressie-Read divergence.
Dead-Direction Signatures (DDS) provide a cheap, closed-form spectral reading of a network's singular complexity.
problem Estimating the complexity of deep networks through their loss singularities.
method DDS replaces the SGLD posterior chain with spectral linear algebra.
result DDS observables rank-track the network's singular complexity at the framework-predicted sign.
The paper develops a neural network to predict wind speed from visual observations.
problem Accurate wind speed prediction for renewable energy and weather forecasting.
method Coupled Convolutional and Recurrent Neural Network architecture trained on visual flow-structure interactions.
result The model accurately predicts wind speeds with low error compared to cup anemometer measurements.
New method speeds up deep neural networks inference.
problem Inference speed of deep neural networks.
method Maximum volume algorithm for reduced-order modeling.
result Convolutional layers can be replaced with smaller fully-connected layers with minimal accuracy loss.
Paper explores zero-shot cross-lingual reading comprehension using pre-trained multi-lingual model.
problem Lack of training data for every language in reading comprehension tasks.
method Systematic exploration of zero-shot cross-lingual transfer learning with a multi-lingual language representation model.
result Zero-shot cross-lingual transfer learning is feasible and translating source data into target language is not necessary.
CNNs improve wind speed forecasts in the Netherlands.
problem Limited spatial patterns in current post-processing methods.
method Convolutional Neural Networks (CNNs) for spatial wind speed information.
result CNNs produce better probabilistic forecasts with higher Brier skill scores.
QAInfomax improves reading comprehension by maximizing mutual information, achieving state-of-the-art performance.
problem Distractor sentences in question answering datasets are hard to distinguish from relevant ones.
method QAInfomax regularizes reading comprehension models to learn mutual information among passages, questions, and answers.
result QAInfomax achieves state-of-the-art performance on Adversarial-SQuAD dataset.
Deep neural network reconstructs traffic speeds from sparse vehicle data.
problem Reconstructing traffic speeds from limited probe vehicle data.
method Convolutional neural network architecture for spatio-temporal learning.
result The method can reconstruct traffic speeds with low probe vehicle penetration.
Metalearned neural memory improves learning across various tasks.
problem Improving neural network adaptability and memory function.
method Augmenting neural networks with a metalearned external memory mechanism.
result The model achieves strong performance on diverse learning problems.
AntMan compresses RNNs for faster inference with minimal accuracy loss.
problem Inference performance, cost, and memory requirements of complex RNN models.
method Structured sparsity combined with low-rank decomposition.
result Up to 100x computation reduction with less than 1pt accuracy drop.
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.
Many Machine Reading and Natural Language Understanding tasks require reading supporting text in order to answer questions. For example, in Question Answering, the supporting text can be newswire or Wikipedia articles; in Natural Language Inference, premises can be seen as the supporting text and hypotheses as question…
Many mobile robots rely on 2D laser scanners for localization, mapping, and navigation. However, those sensors are unable to correctly provide distance to obstacles such as glass panels and tables whose actual occupancy is invisible at the height the sensor is measuring. In this work, instead of estimating the distance…
SparseSense improves HAR from sparse sensor data, outperforming state-of-the-art models.
problem Learning activity recognition from highly sparse sensor data streams.
method Set-based neural networks for end-to-end learning from sparse data.
result Significant performance improvements in HAR from passive sensor datasets.
META2 improves taxonomic classification and abundance estimation in metagenomics with deep learning and memory efficiency.
problem Memory constraints and inefficiencies in taxonomic classification and abundance estimation for metagenomics.
method Developed a novel memory-efficient read classification technique combining deep learning and locality-sensitive hashing, and formulated abundance estimation as a Multiple Instance Learning problem.
result Our approach outperforms conventional methods in both single-read taxonomic classification and abundance estimation, especially when memory is limited.
Unified deep learning for graph signals, simplifying existing models.
problem Efficiency of Convolutional Neural Networks on graph signals.
method Unified formalism for existing deep learning models on graph signals.
result Unified formalism simplifies and compares existing models.
SingleProp speeds up robust neural network training with minimal certification.
problem Efficiently defending neural networks against adversarial attacks with certified guarantees.
method SingleProp regularizer that requires only one forward pass per training iteration.
result Comparable certified accuracy to state-of-the-art defenses, but significantly faster training.
A new algorithm speeds up matrix operations in Neural Networks.
problem Time-consuming matrix operations in Neural Networks.
method An algorithm that increases the degree of parallelism of matrix multiplication.
result The algorithm speeds up several matrix operations in Neural Networks.
Shannon's mathematical theory of communication defines fundamental limits on how much information can be transmitted between the different components of any man-made or biological system. This paper is an informal but rigorous introduction to the main ideas implicit in Shannon's theory. An annotated reading list is pro…
Predicting delayed outcomes is an important problem in recommender systems (e.g., if customers will finish reading an ebook). We formalize the problem as an adversarial, delayed online learning problem and consider how a proxy for the delayed outcome (e.g., if customers read a third of the book in 24 hours) can help mi…
We present a memory augmented neural network for natural language understanding: Neural Semantic Encoders. NSE is equipped with a novel memory update rule and has a variable sized encoding memory that evolves over time and maintains the understanding of input sequences through read}, compose and write operations. NSE c…
New limits found for training deep learning models efficiently.
problem Optimizing the training speed of deep learning models without sacrificing accuracy.
method Applied stochastic thermodynamics to set speed limits for neural network training.
result Training neural networks is optimal within certain scaling assumptions.
We present a graphical criterion for reading dependencies from the minimal directed independence map G of a graphoid p when G is a polytree and p satisfies composition and weak transitivity. We prove that the criterion is sound and complete. We argue that assuming composition and weak transitivity is not too restrictiv…
Recurrent Neural Networks (RNN) are a type of statistical model designed to handle sequential data. The model reads a sequence one symbol at a time. Each symbol is processed based on information collected from the previous symbols. With existing RNN architectures, each symbol is processed using only information from th…
Most work in machine reading focuses on question answering problems where the answer is directly expressed in the text to read. However, many real-world question answering problems require the reading of text not because it contains the literal answer, but because it contains a recipe to derive an answer together with …
Multirate training speeds up neural network fine-tuning.
problem Efficiently fine-tuning deep neural networks.
method Partitioning neural network parameters into fast and slow parts, updating slowly over longer intervals.
result Significant computational speed-up for transfer learning tasks.