arXiv research

Proves unknottedness of certain 3D shapes with multiple ends.

End-to-end KBQA system learns from multiple reasoning paths without labeled paths.

Recently, there has been growing interest in multi-speaker speech recognition, where the utterances of multiple speakers are recognized from their mixture. Promising techniques have been proposed for this task, but earlier works have required additional training data such as isolated source signals or senone alignments…

The study shows ends of shrinking gradient $ρ$-Einstein solitons are non-parabolic.

Grimaldi-Pansu metrics are constructed for manifolds with multiple ends.

In this paper, we propose a new loss function called generalized end-to-end (GE2E) loss, which makes the training of speaker verification models more efficient than our previous tuple-based end-to-end (TE2E) loss function. Unlike TE2E, the GE2E loss function updates the network in a way that emphasizes examples that ar…

Model predicts future values and fills in missing data.

Multi-task learning is a method for improving the generalizability of multiple tasks. In order to perform multiple classification tasks with one neural network model, the losses of each task should be combined. Previous studies have mostly focused on multiple prediction tasks using joint loss with static weights for tr…

asp2vec learns dynamic node aspect distributions for better network embedding.

Study shows certain infinite-ended groups are not quasi-isometrically rigid.

End-to-end Sinkhorn Autoencoder reduces data simulation time with noise generation.

The use of deep neural networks in edge computing devices hinges on the balance between accuracy and complexity of computations. Ternary Connect (TC) \cite{lin2015neural} addresses this issue by restricting the parameters to three levels $-1, 0$, and $+1$, thus eliminating multiplications in the forward pass of the net…

Automated multi-task learning algorithm that optimizes network topology.

Kauri is a novel unsupervised binary tree for clustering that outperforms existing methods.

Recently neural networks and multiple instance learning are both attractive topics in Artificial Intelligence related research fields. Deep neural networks have achieved great success in supervised learning problems, and multiple instance learning as a typical weakly-supervised learning method is effective for many app…

Improves understanding of PWS by calculating influence of sources and data.

This work extracts stochastic dynamical systems with $\alpha$-stable Lévy noise.

Stella Nera accelerates matrix multiplications with a hash-based approach, achieving high energy efficiency and accuracy.

In this paper it is shown that multiplicative cohomology theories that are rationally even -- a technical condition that is often satisfied -- the Hopkins-Singer construction of generalized differential cohomology has a unital, graded commutative multiplicative structure. To this end, an explicit integration and a diff…

Learning to drive faithfully in highly stochastic urban settings remains an open problem. To that end, we propose a Multi-task Learning from Demonstration (MT-LfD) framework which uses supervised auxiliary task prediction to guide the main task of predicting the driving commands. Our framework involves an end-to-end tr…

End-to-end pipeline for data-driven decision making in mixed-integer optimization.

End-to-end approach for weak supervision improves downstream model performance.

Multiple instance learning (MIL) aims to learn the mapping between a bag of instances and the bag-level label. In this paper, we propose a new end-to-end graph neural network (GNN) based algorithm for MIL: we treat each bag as a graph and use GNN to learn the bag embedding, in order to explore the useful structural inf…

We study the problem of generating interesting endings for stories. Neural generative models have shown promising results for various text generation problems. Sequence to Sequence (Seq2Seq) models are typically trained to generate a single output sequence for a given input sequence. However, in the context of a story,…

End-to-end autonomous driving perception learns latent features for better performance.

Study shows generic surfaces avoid complex flow patterns.

The paper counts ends of differential forms on surfaces.

In this work, we propose an end-to-end block-based auto-encoder system for image compression. We introduce novel contributions to neural-network based image compression, mainly in achieving binarization simulation, variable bit rates with multiple networks, entropy-friendly representations, inference-stage code optimiz…

Automatic machine learning (AutoML) is an area of research aimed at automating machine learning (ML) activities that currently require human experts. One of the most challenging tasks in this field is the automatic generation of end-to-end ML pipelines: combining multiple types of ML algorithms into a single architectu…

MultiImport infers node importance from multiple KG signals.

How can we build recommender systems to take into account fairness? Real-world recommender systems are often composed of multiple models, built by multiple teams. However, most research on fairness focuses on improving fairness in a single model. Further, recent research on classification fairness has shown that combin…

We propose an autoencoding sequence-based transceiver for communication over dispersive channels with intensity modulation and direct detection (IM/DD), designed as a bidirectional deep recurrent neural network (BRNN). The receiver uses a sliding window technique to allow for efficient data stream estimation. We find t…

We provide an end-to-end differentially private spectral algorithm for learning LDA, based on matrix/tensor decompositions, and establish theoretical guarantees on utility/consistency of the estimated model parameters. The spectral algorithm consists of multiple algorithmic steps, named as "{edges}", to which noise cou…

The paper proves properties of surfaces with finite curvature in 3D space.

This paper and its sequel prove a generalization of the usual gluing theorem for two index 1 pseudoholomorphic curves u_+ and u_- in the symplectization of a contact 3-manifold. We assume that for each embedded Reeb orbit gamma, the total multiplicity of the negative ends of u_+ at covers of gamma agrees with the total…

New fair regression method improves fairness in chronic kidney disease classification.

Establishes inequality for multiple black holes, proving mass lower bound.

Proposes a defense method against multiple adversarial video types.

Optimizes neural networks by removing unnecessary layers, improving performance and speed.

We construct Weierstrass data for higher genus embedded doubly periodic minimal surfaces and present numerical evidence that the associated period problem can be solved. In the orthogonal ends case, there previously was only one known surface for each genus. We illustrate multiple new examples for each genus g>2. In th…

Segmentation maps of medical images annotated by medical experts contain rich spatial information. In this paper, we propose to decompose annotation maps to learn disentangled and richer feature transforms for segmentation problems in medical images. Our new scheme consists of two main stages: decompose and integrate. …

Proposes a method to classify binary data from multiple unlabeled datasets.

Teaching machines to accomplish tasks by conversing naturally with humans is challenging. Currently, developing task-oriented dialogue systems requires creating multiple components and typically this involves either a large amount of handcrafting, or acquiring costly labelled datasets to solve a statistical learning pr…

Missing data is a significant problem impacting all domains. State-of-the-art framework for minimizing missing data bias is multiple imputation, for which the choice of an imputation model remains nontrivial. We propose a multiple imputation model based on overcomplete deep denoising autoencoders. Our proposed model is…

Study learning from multiple thinkers providing step-by-step solutions to problems.

In this paper we classify branched Willmore spheres with at most three branch points (including multiplicity), showing that they may be obtained from complete minimal surfaces in $\R ^ 3$ with ends of multiplicity at most three. This extends the classification result of Bryant. We then show that this may be applied to …

For decades, context-dependent phonemes have been the dominant sub-word unit for conventional acoustic modeling systems. This status quo has begun to be challenged recently by end-to-end models which seek to combine acoustic, pronunciation, and language model components into a single neural network. Such systems, which…

Convolutional neural networks (CNN) have achieved state of the art performance on both classification and segmentation tasks. Applying CNNs to microscopy images is challenging due to the lack of datasets labeled at the single cell level. We extend the application of CNNs to microscopy image classification and segmentat…