arXiv research

Framework transfers inertial motion across domains without labeled data.

Generative Link Sequence Modeling predicts future links in evolving networks.

In this work we introduce malware detection from raw byte sequences as a fruitful research area to the larger machine learning community. Building a neural network for such a problem presents a number of interesting challenges that have not occurred in tasks such as image processing or NLP. In particular, we note that …

We introduce Embed to Control (E2C), a method for model learning and control of non-linear dynamical systems from raw pixel images. E2C consists of a deep generative model, belonging to the family of variational autoencoders, that learns to generate image trajectories from a latent space in which the dynamics is constr…

A model learns stock trading rules from raw prices using encoder-decoder neural network.

IITNet learns sleep stages from raw EEG using sub-epoch features and temporal contexts.

Method computes embeddings for RNA-seq data without genome alignment.

Sparse Transformers reduce memory and time requirements for long sequence modeling.

GeNet classifies metagenomic sequences with less memory and comparable recall to state-of-the-art methods.

Process Monitoring involves tracking a system's behaviors, evaluating the current state of the system, and discovering interesting events that require immediate actions. In this paper, we consider monitoring temporal system state sequences to help detect the changes of dynamic systems, check the divergence of the syste…

CLVSA predicts financial market trends using LSTM and attention mechanisms.

PRAGMA models financial event sequences for various banking tasks.

RNA-binding proteins (RBPs) play crucial roles in many biological processes, e.g. gene regulation. Computational identification of RBP binding sites on RNAs are urgently needed. In particular, RBPs bind to RNAs by recognizing sequence motifs. Thus, fast locating those motifs on RNA sequences is crucial and time-efficie…

Graph ConvNet improves ncRNA classification accuracy.

Avian Influenza breakouts cause millions of dollars in damage each year globally, especially in Asian countries such as China and South Korea. The impact magnitude of a breakout directly correlates to time required to fully understand the influenza virus, particularly the interspecies pathogenicity. The procedure requi…

Proposes Textual Echo Cancellation to improve speech recognition.

We introduce Deep Variational Bayes Filters (DVBF), a new method for unsupervised learning and identification of latent Markovian state space models. Leveraging recent advances in Stochastic Gradient Variational Bayes, DVBF can overcome intractable inference distributions via variational inference. Thus, it can handle …

The goal of this project is to develop a limited lip reading algorithm for a subset of the English language. We consider a scenario in which no audio information is available. The raw video is processed and the position of the lips in each frame is extracted. We then prepare the lip data for processing and classify the…

Self-driving vehicles improve safety by predicting surrounding vehicles' trajectories.

This paper improves speech recognition by using raw waveform signals in multi-span CNN acoustic models.

Continuous MDS embeds sequences of dissimilarities in Euclidean space.

Reduces data leakage in distributed deep learning models.

Deep neural nets classify sleep stages from raw PSG data with high accuracy.

This study uses deep learning to improve the accuracy of raw data denoising in ProtoDUNE experiments.

Predicting the biological function of molecules, be it proteins or drug-like compounds, from their atomic structure is an important and long-standing problem. Function is dictated by structure, since it is by spatial interactions that molecules interact with each other, both in terms of steric complementarity, as well …

Novel fusion of autoencoders predicts sleepiness from speech.

New method detects RNA modifications without prior training, revealing novel sites.

New method explains classifiers trained on raw hierarchical data.

Existing automatic music generation approaches that feature deep learning can be broadly classified into two types: raw audio models and symbolic models. Symbolic models, which train and generate at the note level, are currently the more prevalent approach; these models can capture long-range dependencies of melodic st…

Chemical reactions can be described as the stepwise redistribution of electrons in molecules. As such, reactions are often depicted using `arrow-pushing' diagrams which show this movement as a sequence of arrows. We propose an electron path prediction model (ELECTRO) to learn these sequences directly from raw reaction …

Jukebox generates high-fidelity songs with singing in raw audio.

A quantum model classifies financial sentiment by mapping text chunks to quantum circuits.

Blow converts non-parallel raw audio voices efficiently.

This paper uses cPF to build recommender systems from raw count data.

Generative Neuro-Symbolic model learns from raw data with rich conceptual representations.

Realistic music generation is a challenging task. When building generative models of music that are learnt from data, typically high-level representations such as scores or MIDI are used that abstract away the idiosyncrasies of a particular performance. But these nuances are very important for our perception of musical…

New system tracks musical performances in raw sheet images without preprocessing.

SSL theory improves representation learning from raw data.

We present a representation learning algorithm that learns a low-dimensional latent dynamical system from high-dimensional \textit{sequential} raw data, e.g., video. The framework builds upon recent advances in amortized inference methods that use both an inference network and a refinement procedure to output samples f…

Perceptor Gradients learns symbolic representations from raw data.

This research improves LSTM for monthly electricity demand forecasting using pattern-based methods.

SplitNN enables deep learning model training without sharing patient data.

Method learns multi-stage tasks from single video, overcoming challenges of raw pixel learning and insufficient demonstrations.

Artificial neural network (ANN) is a very useful tool in solving learning problems. Boosting the performances of ANN can be mainly concluded from two aspects: optimizing the architecture of ANN and normalizing the raw data for ANN. In this paper, a novel method which improves the effects of ANN by preprocessing the raw…

A new algorithm learns from raw feature vectors using deep neural networks and UCB for exploration.

In recent years, deep generative models have been shown to 'imagine' convincing high-dimensional observations such as images, audio, and even video, learning directly from raw data. In this work, we ask how to imagine goal-directed visual plans -- a plausible sequence of observations that transition a dynamical system …

RAW-Explainer generates interpretable subgraph explanations for link predictions in knowledge graphs.

The paper explains knowledge distillation by analyzing visual concepts in DNNs.