Jack the Reader is a framework for machine reading tasks.
problem Machine reading tasks require reading supporting text.
method A framework for quick model prototyping, evaluation, and integration of new datasets.
result Jack supports three tasks: QA, NLI, and Link Prediction.
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.
Formalizes interpreting natural language rules for answering questions, collecting 32k task instances.
problem Interpreting regulations and answering 'Can I...?' or 'Do I have to...?' questions.
method Formalization of task, crowd-sourcing strategy to collect 32k instances, analysis of challenges, evaluation of performance.
result Promising results when no background knowledge is needed, substantial room for improvement when background knowledge is needed.
MAMMO reduces radiologist workload by triaging mammograms, improving accuracy.
problem Reducing radiologist workload while maintaining diagnostic accuracy.
method Developed a clinical decision support system with a multi-task learning CNN and triage network.
result Reduced radiologist workload by 42.8% with improved overall diagnostic accuracy.
Metagenomics characterizes the taxonomic diversity of microbial communities by sequencing DNA directly from an environmental sample. One of the main challenges in metagenomics data analysis is the binning step, where each sequenced read is assigned to a taxonomic clade. Due to the large volume of metagenomics datasets,…
Model generates label-dependent paraphrases for NLP tasks.
problem Generating semantically different paraphrases for NLP tasks.
method Deep variational model with label-dependent generation.
result Model improves generative power of paraphrasing models.
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.
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.
Recent advances in high-throughput cDNA sequencing (RNA-Seq) technology have revolutionized transcriptome studies. A major motivation for RNA-Seq is to map the structure of expressed transcripts at nucleotide resolution. With accurate computational tools for transcript reconstruction, this technology may also become us…
EMR learns to read and remember from streaming data for QA.
problem Scalable QA from streaming data without knowing questions.
method End-to-end deep network model (EMR) with RL agent for memory management.
result EMR achieves significant improvements over existing methods on synthetic and real-world datasets.
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.
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…
In an end-to-end dialog system, the aim of dialog state tracking is to accurately estimate a compact representation of the current dialog status from a sequence of noisy observations produced by the speech recognition and the natural language understanding modules. This paper introduces a novel method of dialog state t…
The ability to use a 2D map to navigate a complex 3D environment is quite remarkable, and even difficult for many humans. Localization and navigation is also an important problem in domains such as robotics, and has recently become a focus of the deep reinforcement learning community. In this paper we teach a reinforce…
This paper sets baselines for reading comprehension benchmarks, finding simple models often perform well.
problem Understanding the difficulty of popular reading comprehension benchmarks.
method Established baselines for bAbI, SQuAD, CBT, CNN, and Who-did-What datasets.
result Simple models often outperform complex models on many benchmarks.
Multi-hop inference is necessary for machine learning systems to successfully solve tasks such as Recognising Textual Entailment and Machine Reading. In this work, we demonstrate the effectiveness of adaptive computation for learning the number of inference steps required for examples of different complexity and that l…
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.
Paper compares ML models for a wall-following robot, achieving high accuracy.
problem Improving prediction accuracy of a wall-following robot's direction.
method Trained various machine learning models on a dataset of ultrasound sensor readings.
result Presented machine learning models with higher accuracy than previous work.
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.
Survey analyzes economic research on cryptocurrencies using hybrid methods.
problem Lack of comprehensive literature review in cryptocurrencies economic research.
method Dual analysis combining bibliometric and close literature review.
result Updated state of cryptocurrency economic research literature.
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.
Enhanced QANet tackles unanswerable questions in MRC.
problem Improving performance on unanswerable questions in MRC.
method Extends QANet architecture to handle unanswerable questions through multi-task learning.
result EQuANt achieves close to 2x better performance on SQuAD 2 compared to baseline.
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.
Paper uses ensemble learning for IoT cybersecurity anomaly detection.
problem Anomaly detection in IoT data is challenging due to heterogeneous device types.
method Bayesian hyperparameter optimisation for ensemble learning.
result Ensemble learning with Bayesian optimisation improves anomaly detection accuracy.
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…
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.
Extends GENO framework for GPU optimization of constrained ML problems.
problem Constrained optimization in classical machine learning.
method Extends GENO framework to GPU optimization, specifying problems in a modeling language.
result Solvers on GPU outperform state-of-the-art approaches by several orders of magnitude.
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.
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…
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…
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.
Lecture note for data science students on machine learning basics and advanced topics.
problem No specific problem stated; preparing students for advanced machine learning.
method Introduction of basic machine learning concepts and advanced topics.
result Students are prepared to study advanced machine learning topics.
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…
TDA classifies MNIST digits with reduced feature set.
problem Classifying MNIST digits using machine learning.
method Persistent homology for feature generation and classification.
result 5x reduction in feature set size with similar accuracy.
Morpheo is a transparent and secure machine learning platform collecting and analysing large datasets. It aims at building state-of-the art prediction models in various fields where data are sensitive. Indeed, it offers strong privacy of data and algorithm, by preventing anyone to read the data, apart from the owner an…
Interactive machine comprehension models learn through seeking relevant information.
problem Existing MRC models struggle with real-world applications due to static datasets.
method Reframe MRC datasets as interactive, partially observable environments.
result Interactive models can seek relevant information through sequential decision making.
LectureBank helps students find the right NLP course sequence.
problem Finding the right NLP course sequence for students with no background.
method Embedding-based method and neural graph-based networks to learn prerequisite relations.
result LectureBank dataset aids in educational and application purposes.
New method combines personal and reference genomes for better machine learning in DNA sequencing.
problem Improving accuracy of genetic variant calls in sequencing data.
method Interlaces personal and reference genomes to generate images for machine learning.
result Significant improvement in germline variant calling and somatic variant calling across tumor/normal data.
Speech Translation has always been about giving source text or audio input and waiting for system to give translated output in desired form. In this paper, we present the Acoustic Dialect Decoder (ADD) - a voice to voice ear-piece translation device. We introduce and survey the recent advances made in the field of Spee…
We show how the rotation and translation fields of a surface, introduced by G. Darboux, may be used to obtain short proofs of a well-known theorem (that reads that the total mean curvature of a surface is stationary under an infinitesimal bending) and a new theorem (that reads that every infinitesimal flex of any simpl…
This work tackles missing annotations in large sensor datasets.
problem Missing annotations in large sensor datasets negatively affect supervised learning system performance.
method Proposes and evaluates three paradigms to handle gaps: dropping, single label, and unique label, along with a hybrid combination.
result Evaluation of proposed paradigms and hybrid combination shows significant performance improvement.
OMD monitors stock market dynamics through matrix trajectories and reveals crisis patterns.
problem Understanding and predicting stock market crises and sector rotations.
method Applying OMD to S\&P 500 returns over three crises, analyzing distance matrices and their spectra.
result Market dynamics show coherent changes during crises, with distinct sector leadership.
Study prenatal PM2.5 exposure and 4th grade reading scores, identifying critical windows of susceptibility.
problem Understanding the impact of prenatal PM2.5 exposure on educational outcomes.
method Developed a locally adaptive Bayesian regression model with B-spline basis expansion and dynamic shrinkage priors.
result Prenatal PM2.5 exposure during early and late pregnancy is most adverse for 4th grade reading scores.
Survey of techniques for automating hyperparameter optimization in machine learning.
problem Finding optimal hyperparameters for machine learning algorithms.
method Review of various hyperparameter optimization techniques.
result Unified treatment of hyperparameter optimization techniques.
The covariance graph (aka bi-directed graph) of a probability distribution p is the undirected graph G where two nodes are adjacent iff their corresponding random variables are marginally dependent in p. In this paper, we present a graphical criterion for reading dependencies from G, under the assumption that $…
Bandana stores deep learning models using NVM with DRAM caching.
problem Reducing memory footprint of deep learning models stored on DRAM.
method Uses NVM as primary storage, DRAM as cache, hypergraph partitioning, and cache simulation.
result Significantly reduces the cost of ownership for storing deep learning models.
FEM improves attention mechanisms by applying value-driven log-linear tilts.
problem Standard attention mechanisms read via convex average, limiting channel-wise selection.
method Free Energy Mixer (FEM) applies a value-driven, per-channel log-linear tilt to a fast prior over indices.
result FEM outperforms strong baselines on NLP, vision, and time-series tasks.