English
Related papers

Related papers: SEARNN: Training RNNs with Global-Local Losses

200 papers

Exploration is a fundamental challenge in reinforcement learning (RL). Many of the current exploration methods for deep RL use task-agnostic objectives, such as information gain or bonuses based on state visitation. However, many practical…

Machine Learning · Computer Science 2018-02-21 Abhishek Gupta , Russell Mendonca , YuXuan Liu , Pieter Abbeel , Sergey Levine

Large neural networks are typically trained for a fixed computational budget, creating a rigid trade-off between performance and efficiency that is ill-suited for deployment in resource-constrained or dynamic environments. Existing…

Machine Learning · Computer Science 2026-03-05 Paulius Rauba , Mihaela van der Schaar

The standard approach to mitigate errors made by an automatic speech recognition system is to use confidence scores associated with each predicted word. In the simplest case, these scores are word posterior probabilities whilst more complex…

Audio and Speech Processing · Electrical Eng. & Systems 2019-02-19 Qiujia Li , Preben Ness , Anton Ragni , Mark Gales

A sound event detection (SED) method typically takes as an input a sequence of audio frames and predicts the activities of sound events in each frame. In real-life recordings, the sound events exhibit some temporal structure: for instance,…

Sound · Computer Science 2019-11-07 Konstantinos Drossos , Shayan Gharib , Paul Magron , Tuomas Virtanen

This paper investigates the intriguing question of whether we can create learning algorithms that automatically generate training data, learning environments, and curricula in order to help AI agents rapidly learn. We show that such…

Machine Learning · Computer Science 2019-12-18 Felipe Petroski Such , Aditya Rawal , Joel Lehman , Kenneth O. Stanley , Jeff Clune

Vanishing long-term gradients are a major issue in training standard recurrent neural networks (RNNs), which can be alleviated by long short-term memory (LSTM) models with memory cells. However, the extra parameters associated with the…

Computation and Language · Computer Science 2018-02-26 Chao Zhang , Philip Woodland

This study introduces a structural-based training approach for CNN-based algorithms in single-molecule localization microscopy (SMLM) and 3D object reconstruction. We compare this approach with the traditional random-based training method,…

Computer Vision and Pattern Recognition · Computer Science 2023-10-02 Armin Abdehkakha , Craig Snoeyink

To avoid the exhaustive search over locations and scales, current state-of-the-art object detection systems usually involve a crucial component generating a batch of candidate object proposals from images. In this paper, we present a simple…

Computer Vision and Pattern Recognition · Computer Science 2018-07-31 Tianshui Chen , Liang Lin , Xian Wu , Nong Xiao , Xiaonan Luo

Despite the success of sequence-to-sequence approaches in automatic speech recognition (ASR) systems, the models still suffer from several problems, mainly due to the mismatch between the training and inference conditions. In the…

Computation and Language · Computer Science 2018-03-01 Andros Tjandra , Sakriani Sakti , Satoshi Nakamura

Recently, graph neural networks (GNNs) have shown its unprecedented success in many graph-related tasks. However, GNNs face the label scarcity issue as other neural networks do. Thus, recent efforts try to pre-train GNNs on a large-scale…

Machine Learning · Computer Science 2024-03-04 Zhili Wang , Shimin Di , Lei Chen , Xiaofang Zhou

Recurrent neural networks (RNNs) can be interpreted as discrete-time state-space models, where the state evolution corresponds to an infinite-impulse-response (IIR) filtering operation governed by both feedforward weights and recurrent…

Machine Learning · Computer Science 2026-02-26 Alexander Morgan , Ummay Sumaya Khan , Lingjia Liu , Lizhong Zheng

Pair-based metric learning has been widely adopted to learn sentence embedding in many NLP tasks such as semantic text similarity due to its efficiency in computation. Most existing works employed a sequence encoder model and utilized…

Computation and Language · Computer Science 2020-05-26 Li Zhang , Han Wang , Lingxiao Li

Deep neural networks tend to underestimate uncertainty and produce overly confident predictions. Recently proposed solutions, such as MC Dropout and SDENet, require complex training and/or auxiliary out-of-distribution data. We propose a…

Machine Learning · Computer Science 2021-10-14 Akib Mashrur , Wei Luo , Nayyar A. Zaidi , Antonio Robles-Kelly

While language models have shown remarkable performance across diverse tasks, they still encounter challenges in complex reasoning scenarios. Recent research suggests that language models trained on linearized search traces toward…

Artificial Intelligence · Computer Science 2025-10-28 Seungyong Moon , Bumsoo Park , Hyun Oh Song

Neural networks are powerful and flexible models that work well for many difficult learning tasks in image, speech and natural language understanding. Despite their success, neural networks are still hard to design. In this paper, we use a…

Machine Learning · Computer Science 2017-02-16 Barret Zoph , Quoc V. Le

Recurrent Neural Networks (RNNs) achieve state-of-the-art results in many sequence-to-sequence modeling tasks. However, RNNs are difficult to train and tend to suffer from overfitting. Motivated by the Data Processing Inequality (DPI), we…

Machine Learning · Statistics 2018-05-24 Ziv Aharoni , Gal Rattner , Haim Permuter

Many real-world datasets are time series that are sequentially collected and contain rich temporal information. Thus, a common interest in practice is to capture dynamics of time series and predict their future evolutions. To this end, the…

Machine Learning · Computer Science 2025-05-12 Yifan Zhou , Yibo Wang , Chao Shang

The recurrent neural network-transducer (RNNT) is a promising approach for automatic speech recognition (ASR) with the introduction of a prediction network that autoregressively considers linguistic aspects. To train the autoregressive…

Audio and Speech Processing · Electrical Eng. & Systems 2023-05-26 Takafumi Moriya , Takanori Ashihara , Hiroshi Sato , Kohei Matsuura , Tomohiro Tanaka , Ryo Masumura

In this paper, we present a Neural Network (NN) model based on Neural Architecture Search (NAS) and self-learning for received signal strength (RSS) map reconstruction out of sparse single-snapshot input measurements, in the case where…

Machine Learning · Computer Science 2021-05-18 Aleksandra Malkova , Loic Pauletto , Christophe Villien , Benoit Denis , Massih-Reza Amini

Deep Reinforcement Learning has enabled the learning of policies for complex tasks in partially observable environments, without explicitly learning the underlying model of the tasks. While such model-free methods achieve considerable…

Machine Learning · Computer Science 2017-01-11 Tanmay Shankar , Santosha K. Dwivedy , Prithwijit Guha
‹ Prev 1 3 4 5 6 7 10 Next ›