English
Related papers

Related papers: full-FORCE: A Target-Based Method for Training Rec…

200 papers

Recurrent neural networks in the chaotic regime exhibit complex dynamics reminiscent of high-level cortical activity during behavioral tasks. However, existing training methods for such networks are either biologically implausible, or…

Neurons and Cognition · Quantitative Biology 2015-12-09 Thomas Miconi

Bootstrapping is behind much of the successes of deep Reinforcement Learning. However, learning the value function via bootstrapping often leads to unstable training due to fast-changing target values. Target Networks are employed to…

This paper describes an application of reinforcement learning to the mention detection task. We define a novel action-based formulation for the mention detection task, in which a model can flexibly revise past labeling decisions by grouping…

Computation and Language · Computer Science 2017-03-14 Georgiana Dinu , Wael Hamza , Radu Florian

Deep transfer learning recently has acquired significant research interest. It makes use of pre-trained models that are learned from a source domain, and utilizes these models for the tasks in a target domain. Model-based deep transfer…

Computer Vision and Pattern Recognition · Computer Science 2018-11-27 Tianyang Wang , Jun Huan , Michelle Zhu

This work explores the feasibility of steering a drone with a (recurrent) neural network, based on input from a forward looking camera, in the context of a high-level navigation task. We set up a generic framework for training a network to…

Computer Vision and Pattern Recognition · Computer Science 2017-02-27 Klaas Kelchtermans , Tinne Tuytelaars

Deep learning-based Magnetic Resonance (MR) reconstruction methods have focused on generating high-quality images but often overlook the impact on downstream tasks (e.g., segmentation) that utilize the reconstructed images. Cascading…

Image and Video Processing · Electrical Eng. & Systems 2025-06-25 Hwihun Jeong , Se Young Chun , Jongho Lee

We propose a framework for training multiple neural networks simultaneously. The parameters from all models are regularised by the tensor trace norm, so that each neural network is encouraged to reuse others' parameters if possible -- this…

Machine Learning · Computer Science 2017-02-20 Yongxin Yang , Timothy M. Hospedales

Learning automatically the best activation function for the task is an active topic in neural network research. At the moment, despite promising results, it is still difficult to determine a method for learning an activation function that…

Machine Learning · Computer Science 2019-10-29 Andrea Apicella , Francesco Isgrò , Roberto Prevete

Two less addressed issues of deep reinforcement learning are (1) lack of generalization capability to new target goals, and (2) data inefficiency i.e., the model requires several (and often costly) episodes of trial and error to converge,…

Computer Vision and Pattern Recognition · Computer Science 2016-09-19 Yuke Zhu , Roozbeh Mottaghi , Eric Kolve , Joseph J. Lim , Abhinav Gupta , Li Fei-Fei , Ali Farhadi

Recurrent neural networks (RNNs) are omnipresent in sequence modeling tasks. Practical models usually consist of several layers of hundreds or thousands of neurons which are fully connected. This places a heavy computational and memory…

Machine Learning · Computer Science 2019-05-30 Matthijs Van Keirsbilck , Alexander Keller , Xiaodong Yang

Developing autonomous agents that can interact with changing environments is an open challenge in machine learning. Robustness is particularly important in these settings as agents are often fit offline on expert demonstrations but deployed…

Machine Learning · Computer Science 2023-12-01 Neehal Tumma , Mathias Lechner , Noel Loo , Ramin Hasani , Daniela Rus

Model-based next state prediction and state value prediction are slow to converge. To address these challenges, we do the following: i) Instead of a neural network, we do model-based planning using a parallel memory retrieval system (which…

Artificial Intelligence · Computer Science 2023-02-02 John Chong Min Tan , Mehul Motani

This paper explores learned-context neural networks. It is a multi-task learning architecture based on a fully shared neural network and an augmented input vector containing trainable task parameters. The architecture is interesting due to…

Machine Learning · Computer Science 2025-08-07 Anders T. Sandnes , Bjarne Grimstad , Odd Kolbjørnsen

We introduce techniques for rapidly transferring the information stored in one neural net into another neural net. The main purpose is to accelerate the training of a significantly larger neural net. During real-world workflows, one often…

Machine Learning · Computer Science 2016-04-26 Tianqi Chen , Ian Goodfellow , Jonathon Shlens

Recently, the Transformer model that is based solely on attention mechanisms, has advanced the state-of-the-art on various machine translation tasks. However, recent studies reveal that the lack of recurrence hinders its further improvement…

Computation and Language · Computer Science 2019-04-08 Jie Hao , Xing Wang , Baosong Yang , Longyue Wang , Jinfeng Zhang , Zhaopeng Tu

This paper proposes a physics-informed learning framework for a class of recurrent neural networks tailored to large-scale and networked systems. The approach aims to learn control-oriented models that preserve the structural and stability…

Systems and Control · Electrical Eng. & Systems 2026-03-27 Daniele Ravasio , Claudia Sbardi , Marcello Farina , Andrea Ballarino

A temporal point process is a mathematical model for a time series of discrete events, which covers various applications. Recently, recurrent neural network (RNN) based models have been developed for point processes and have been found…

Machine Learning · Computer Science 2020-01-13 Takahiro Omi , Naonori Ueda , Kazuyuki Aihara

We present a novel training method for deep operator networks (DeepONets), one of the most popular neural network models for operators. DeepONets are constructed by two sub-networks, namely the branch and trunk networks. Typically, the two…

Numerical Analysis · Mathematics 2023-09-06 Sanghyun Lee , Yeonjong Shin

Training deep learning models takes an extremely long execution time and consumes large amounts of computing resources. At the same time, recent research proposed systems and compilers that are expected to decrease deep learning models…

Machine Learning · Computer Science 2022-05-11 Sean Parker , Sami Alabed , Eiko Yoneki

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