English
Related papers

Related papers: Technical Report: Combining knowledge from Transfe…

200 papers

In this paper we present an alternative strategy for fine-tuning the parameters of a network. We named the technique Gradual Tuning. Once trained on a first task, the network is fine-tuned on a second task by modifying a progressively…

Artificial Intelligence · Computer Science 2017-11-29 Guglielmo Montone , J. Kevin O'Regan , Alexander V. Terekhov

Based on a natural connection between ResNet and transport equation or its characteristic equation, we propose a continuous flow model for both ResNet and plain net. Through this continuous model, a ResNet can be explicitly constructed as a…

Machine Learning · Computer Science 2017-12-12 Zhen Li , Zuoqiang Shi

In this paper, we describe a phenomenon, which we named "super-convergence", where neural networks can be trained an order of magnitude faster than with standard training methods. The existence of super-convergence is relevant to…

Machine Learning · Computer Science 2018-05-18 Leslie N. Smith , Nicholay Topin

In comparison to classical shallow representation learning techniques, deep neural networks have achieved superior performance in nearly every application benchmark. But despite their clear empirical advantages, it is still not well…

Machine Learning · Computer Science 2022-01-11 Calvin Murdock , George Cazenavette , Simon Lucey

Dominant sequence models like the Transformer represent structure implicitly through dense attention weights, incurring quadratic complexity. We propose RewriteNets, a novel neural architecture built on an alternative paradigm: explicit,…

Machine Learning · Computer Science 2026-01-14 Harshil Vejendla

In recent years, deep learning models have shown great potential in source code modeling and analysis. Generally, deep learning-based approaches are problem-specific and data-hungry. A challenging issue of these approaches is that they…

Machine Learning · Computer Science 2020-07-15 Yasir Hussain , Zhiqiu Huang , Yu Zhou , Senzhang Wang

Large, pre-trained models are problematic to use in resource constrained applications. Fortunately, task-aware structured pruning methods offer a solution. These approaches reduce model size by dropping structural units like layers and…

Computation and Language · Computer Science 2023-11-14 Lucio Dery , David Grangier , Awni Hannun

Deep learning has achieved state-of-the-art accuracies on several computer vision tasks. However, the computational and energy requirements associated with training such deep neural networks can be quite high. In this paper, we propose a…

Computer Vision and Pattern Recognition · Computer Science 2020-03-04 Aosong Feng , Priyadarshini Panda

Transfer learning with models pretrained on ImageNet has become a standard practice in computer vision. Transfer learning refers to fine-tuning pretrained weights of a neural network on a downstream task, typically unrelated to ImageNet.…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Xander Coetzer , Arné Schreuder , Anna Sergeevna Bosman

Retentive Network (RetNet) represents a significant advancement in neural network architecture, offering an efficient alternative to the Transformer. While Transformers rely on self-attention to model dependencies, they suffer from high…

Computation and Language · Computer Science 2025-06-10 Haiqi Yang , Zhiyuan Li , Yi Chang , Yuan Wu

The online learning of deep neural networks is an interesting problem of machine learning because, for example, major IT companies want to manage the information of the massive data uploaded on the web daily, and this technology can…

Machine Learning · Computer Science 2015-06-16 Sang-Woo Lee , Min-Oh Heo , Jiwon Kim , Jeonghee Kim , Byoung-Tak Zhang

One of the main challenges of deep learning methods is the choice of an appropriate training strategy. In particular, additional steps, such as unsupervised pre-training, have been shown to greatly improve the performances of deep…

Machine Learning · Statistics 2017-11-01 Thomas Moreau , Julien Audiffren

Recurrent neural networks have been widely used in sequence learning tasks. In previous studies, the performance of the model has always been improved by either wider or deeper structures. However, the former becomes more prone to…

Machine Learning · Computer Science 2019-11-20 Yu-Xuan Li , Jin-Yuan Liu , Liang Li , Xiang Guan

The trend towards increasingly deep neural networks has been driven by a general observation that increasing depth increases the performance of a network. Recently, however, evidence has been amassing that simply increasing depth may not be…

Computer Vision and Pattern Recognition · Computer Science 2016-12-01 Zifeng Wu , Chunhua Shen , Anton van den Hengel

Transfer learning is a valuable tool in deep learning as it allows propagating information from one "source dataset" to another "target dataset", especially in the case of a small number of training examples in the latter. Yet,…

Machine Learning · Computer Science 2023-06-13 Daniel Jakubovitz , David Uliel , Miguel Rodrigues , Raja Giryes

Widespread deployment of relays can yield a significant boost in the throughput of forthcoming wireless networks. However, the optimal operation of large relay networks is still infeasible. This paper presents two approaches for the…

Signal Processing · Electrical Eng. & Systems 2023-08-25 Itsik Bergel

Deep learning models are yielding increasingly better performances thanks to multiple factors. To be successful, model may have large number of parameters or complex architectures and be trained on large dataset. This leads to large…

Machine Learning · Computer Science 2022-12-20 Jean-Roch Vlimant , Junqi Yin

Meta-Learning is a subarea of Machine Learning that aims to take advantage of prior knowledge to learn faster and with fewer data [1]. There are different scenarios where meta-learning can be applied, and one of the most common is algorithm…

Machine Learning · Computer Science 2019-10-17 Gean Trindade Pereira , Moisés dos Santos , Edesio Alcobaça , Rafael Mantovani , André Carvalho

Residual connections remain ubiquitous in modern neural network architectures nearly a decade after their introduction. Their widespread adoption is often credited to their dramatically improved trainability: residual networks train faster,…

Machine Learning · Computer Science 2025-06-18 Christian H. X. Ali Mehmeti-Göpel , Michael Wand

Deep neural networks can achieve great successes when presented with large data sets and sufficient computational resources. However, their ability to learn new concepts quickly is limited. Meta-learning is one approach to address this…

Machine Learning · Computer Science 2021-04-22 Mike Huisman , Jan N. van Rijn , Aske Plaat