Ends and cohomology theory for noncompact spaces.
problem Study of noncompact spaces and their invariants.
method Exposition of ends theory, introduction of reduced end cohomology, proof of theorems.
result Proof of a theorem on end cohomology of end sums of manifolds.
End-to-end portfolio system accounts for model risk.
problem Model risk in portfolio selection.
method Distributionally robust optimization with convex duality.
result Explicitly accounts for model risk in portfolio selection.
Improved speech recognition models with data augmentation and dropout.
problem Overfitting in end-to-end speech recognition models.
method Data augmentation and dropout applied to all layers of the network.
result Combination of data augmentation and dropout gives over 20% performance improvement.
New family of trinoids with irregular end found.
problem Finding constant mean curvature trinoids with irregular ends.
method Constructing a five-parameter family of trinoids.
result New family of trinoids with one irregular end.
Develops Bayesian approach for end-to-end learning in stochastic optimization.
problem Stochastic optimization problems under uncertainty.
method Bayesian interpretation and new end-to-end learning algorithms.
result Improved decision maps for empirical risk minimization and distributionally robust optimization.
Study shows mapping class groups are one-ended for surfaces with at least one end.
problem Analyzing the number of ends in mapping class groups of surfaces.
method Proving the associated translatable curve graph is one-ended, quasi-isometric to the mapping class group.
result Mapping class groups are one-ended for surfaces with at least one end of discrete type.
We give a mathematical foundation for, and numerical demonstration of, the existence of mean curvature 1 surfaces of genus 1 with either two elliptic ends or two hyperbolic ends in de Sitter 3-space. An end of a mean curvature 1 surface is an ``elliptic end'' (resp. a ``hyperbolic end'') if the monodromy matrix at the …
End-to-end models perform better with learned log-scaled mel-spectrogram features.
problem End-to-end neural network models struggle with performance compared to models using high-level data representations.
method Trained first layers of a CNN model on log-scaled mel-spectrogram transformation and then used these learned features to initialize an end-to-end CNN classifier.
result Convergence and performance on ESC-50 dataset are similar to a model trained on pre-processed log-scaled mel-spectrogram features.
End-to-end speech recognition system trained on GPUs and CPUs.
problem Building state-of-the-art speech recognition systems.
method Utilizes CPUs and GPUs for training, data augmentation, and neural network updates. Uses vocal tract length perturbation and acoustic simulator for data augmentation. Employed Horovod allreduce for training.
result Achieved 7.92% WER on proprietary English Bixby open domain test set using a Bidirectional Full Attention (BFA) model.
End-to-end autonomous driving models get better uncertainty estimates.
problem Uncertainty quantification for end-to-end autonomous driving models.
method Approximate inference for implicit copula neural linear model.
result Densities for steering angle are marginally calibrated.
End-to-end TTS framework uses hard alignment to improve accuracy.
problem End-to-end TTS systems struggle with accurate alignment between input text and output acoustic features.
method Proposes a constrained alignment scheme with hard monotonic alignments, marginalized during training.
result Improves alignment learning and prediction in end-to-end TTS systems.
This work proposes splitting deep neural networks into smaller sub-networks for faster and more efficient distillation.
problem Challenges in training deep neural networks, including local optima, gradient issues, and computational demands.
method Proposes a non-end-to-end distillation approach by splitting networks into smaller, independent sub-networks (neighbourhoods).
result Independent training of smaller sub-networks can speed up distillation and improve efficiency in various applications.
End-to-end autonomous driving perception learns latent features for better performance.
problem Current autonomous driving systems are complex and require human engineering.
method Sequential latent representation learning for end-to-end perception.
result End-to-end perception model solves detection, tracking, localization, and mapping problems.
End-to-end learning refers to training a possibly complex learning system by applying gradient-based learning to the system as a whole. End-to-end learning system is specifically designed so that all modules are differentiable. In effect, not only a central learning machine, but also all "peripheral" modules like repre…
End-to-end TTS learns context features from text input.
problem Lack of understanding of context features learned by end-to-end TTS.
method Evaluated encoder outputs against context criteria derived from parametric TTS.
result Encoder outputs reflect linguistic and phonetic context features.
End-to-end model extracts nested terms without extra features.
problem Automatic term extraction for nested terms.
method Deep learning model that predicts conceptual terms within fixed sentence lengths.
result High recall and comparable precision on term extraction task.
Study end sum for surfaces and prove uniqueness results.
problem Uniqueness of end sum for surfaces and related manifolds.
method Analyzing end sum and adding a 1-handle at infinity for surfaces.
result The end sum of two surfaces with compact boundary is uniquely determined by the chosen ends.
Study of non-metrizable manifolds' ends, generalizing Nyikos's theorem.
problem Characterizing non-metrizable surfaces with ends.
method Introducing short and long ends, developing theory of spaces of ends.
result Characterization of surfaces as metrizable manifolds plus long pipes.
Machine learning optimizes fiber communication rates without channel knowledge.
problem Achieving information rates in nonlinear fiber communication.
method Jointly optimizes input and auxiliary channel distributions using end-to-end autoencoder learning.
result Computes achievable information rates without explicit channel knowledge.
Hybrid and end-to-end models compare in syllable recognition.
problem Comparing hybrid and end-to-end models for syllable recognition.
method Traditional hybrid system (kaldi) vs. end-to-end (TensorFlow) models.
result Hybrid models with explicit syllable knowledge outperform end-to-end models.
End-to-end autonomous driving framework using guided auxiliary supervision.
problem Learning to drive in highly stochastic urban settings.
method Multi-task Learning from Demonstration (MT-LfD) framework with end-to-end trainable network and supervised auxiliary tasks.
result Joint learning and supervised guidance facilitate faster and better driving performance.
Kauri is a novel unsupervised binary tree for clustering that outperforms existing methods.
problem Learning a tree end-to-end for clustering without labels is an open challenge.
method Greedy maximization of the kernel KMeans objective without centroids.
result Kauri often outperforms existing unsupervised clustering methods, especially with non-linear kernels.
Paper constructs a minimal surface with specific ends and curvature.
problem Constructing a minimal surface with specific topological and geometric properties.
method Weierstrass representation, elliptic functions, and solving the period problem.
result Existence of a complete immersed minimal surface of genus one with specified ends and total Gauss curvature.
Researchers found multiple ways to end-sum 4-manifolds, contradicting a previous conjecture.
problem Nonuniqueness of end-sums in 4-manifolds.
method Explicit examples and detailed discussion of end-cohomology algebra.
result Uncountably many distinct proper homotopy types from end-sums.
End-to-end solution for recognizing handwritten numerals, avoiding traditional preprocessing steps.
problem Handwritten numeral string recognition with traditional preprocessing steps.
method YoLo-based model for automatic detection and recognition, avoiding heuristic-based preprocessing and segmentation.
result Proposed method reduces complexity and is a feasible end-to-end solution for numeral string recognition.
New Hilbert bundles with ends defined from indexed bases.
problem Defining new structures in Hilbert bundles.
method Indexed bases and unitary operators of finite propagation.
result Characteristic classes of Hilbert bundles with ends.
End-to-end policy learning improves statistical arbitrage trading.
problem Traditional mean reversion trading strategies in statistical arbitrage are limited.
method We use Autoencoder architectures and policy learning to develop trading strategies.
result End-to-end training yields superior gross returns.
Estimates ends of Ricci shrinkers, focusing on smooth and singular cases.
problem Understanding the structure of ends in Ricci shrinkers, especially singular ones.
method Analyzes general and asymptotically conical ends, applies to weak convergence.
result No new conical end can form in the limit of sequences of Ricci shrinkers.
End-to-end audio recognition system improves accuracy.
problem Improving accuracy in auditory object recognition.
method Proposes an end-to-end deep neural network with an 'inception nucleus' to learn features from raw waveforms.
result Bests current state-of-the-art approaches by 10.4 percentage points on Urbansound8k dataset.
FPETS speeds up TTS by 600X and reduces errors.
problem High latency and errors in end-to-end TTS systems.
method Non-autoregressive, fully parallel approach with UFANS and trainable position encoding.
result Significant speed up and better quality audios with fewer errors.
Graphemes outperform phonemes in end-to-end models for English Voice-search and multi-dialect tasks.
problem Comparing phoneme-based and grapheme-based sub-word units in end-to-end models.
method Detailed experiments comparing phoneme-based and grapheme-based end-to-end models on large vocabulary English Voice-search and multi-dialect tasks.
result Graphemes outperform phonemes in end-to-end models for English Voice-search and multi-dialect tasks.
End-to-end neural network clusters data in one pass.
problem Clustering high-dimensional data like images and speech.
method Trains a neural network to directly output cluster assignments based on perceptual similarity.
result Demonstrates promising performance on COIL-100 and TIMIT datasets.
Derives an index formula for families of end-periodic Dirac operators.
problem Calculating the index of families of end-periodic Dirac operators.
method Using the renormalized Chern character and Fourier-Laplace transform of the Bismut superconnection.
result Establishes an index formula involving a new end-periodic eta form.
Finite genus embedded minimal surfaces have limited limit ends.
problem Characterizing limit ends of embedded minimal surfaces.
method Proving properties of limit ends and using them to deduce surface characteristics.
result Embedded minimal surfaces with finite genus have at most two limit ends.
End-to-end speech recognition using EEG without speech input.
problem Speech recognition without direct speech input.
method Implemented attention model and CTC-based ASR systems for EEG signals; fused EEG with noisy speech features.
result Demonstrated end-to-end speech recognition using EEG signals.
End-to-end deep learning boosts IM/DD fiber communication over dispersive channels.
problem Improving data transmission over dispersive IM/DD channels with memory.
method Bidirectional recurrent neural network (BRNN) for end-to-end deep learning of the communication system.
result End-to-end SBRNN achieves significant bit-error-rate reduction compared to FFNNs.
New maxfaces with Enneper ends found.
problem Existence of higher-genus maxfaces with specific ends.
method Proved existence through mathematical proof.
result Existence of new maxfaces with Enneper ends.
The study counts ends on shrinkers using geometric covering methods.
problem Counting the number of ends on shrinkers.
method Geometric covering method to study the number of ends.
result Proves that the number of ends on any complete non-compact shrinker is at most polynomial growth with fixed degree.
End-to-end policy learning method improves CATE estimation.
problem Learning optimal treatment policies from partially observed data.
method Modified causal forest for policy learning.
result Maximizing policy value is equivalent to minimizing CATE.
Paper tackles end-to-end training of complex neural networks using DIP method.
problem Training complex heterogeneous neural network models end-to-end.
method Deep Innovation Protection (DIP) method using multiobjective optimization.
result End-to-end training of complex heterogeneous neural network models is possible.
DPFs learn state estimation with algorithmic priors, improving accuracy and generalization.
problem State estimation in complex systems.
method Differentiable particle filters with learnable models.
result End-to-end learning improves state estimation performance by ~80%.
End-to-end Sanskrit TTS developed with limited data, achieving good quality.
problem Developing natural-sounding speech for Sanskrit with scarce data.
method Fine-tuning Tacotron2 model with WaveGlow and transfer learning.
result Achieved an overall MOS of 3.38 from 37 evaluators.
End-to-end system improves multi-speaker speech recognition.
problem Efficiently recognizing speech from multiple speakers without additional training data.
method End-to-end sequence-to-sequence framework with unified source separation and recognition.
result 83.1% relative improvement in multi-speaker speech recognition.
End-to-end model detects articulatory features from speech data.
problem Detecting articulatory features from speech data for various applications.
method Apply Listen, Attend and Spell (LAS) architecture and attention models.
result End-to-end training of manners and places of articulation detectors.
Survey on manifold ends with new heat kernel estimates.
problem Analyzing geometric properties on manifolds with ends.
method Constructing manifolds with ends and analyzing their heat kernel estimates.
result Found manifolds with ends that have different heat kernel estimates.
Free groups can be end homogeneity groups of 3-manifolds.
problem Tackling the possibility of free groups as end homogeneity groups of 3-manifolds.
method Constructing specific 3-manifolds with end homogeneity groups isomorphic to free groups.
result For every finitely generated free group, there exists an irreducible open 3-manifold with that group as its end homogeneity group.
Recent work on discriminative segmental models has shown that they can achieve competitive speech recognition performance, using features based on deep neural frame classifiers. However, segmental models can be more challenging to train than standard frame-based approaches. While some segmental models have been success…
Optimal Poincaré constant estimates on manifolds with ends.
problem Estimating the Poincaré constant on manifolds with ends.
method Heat kernel estimates extended to manifolds with ends, focusing on central balls.
result The Poincaré constant is determined by the second largest end.