Home »
Academic Articles & Research Papers
Showing 16 of 16 academic articles
Jiahui Yu, Linjie Yang, Ning Xu, Yang, Jianchao et al. • arXiv (Cornell University)
(2018)
We present a simple and general method to train a single neural network executable at different widths (number of channels in a layer), permitting instant and adaptive accuracy-efficiency trade-offs at runtime. Instead of training individua...
OPENALEX
Open Access
DOI: https://doi.org/10.48550/arxiv.1812.08928
Itay Hubara, Matthieu Courbariaux, Daniel Soudry, Ran El‐Yaniv et al. • arXiv (Cornell University)
(2016)
We introduce a method to train Quantized Neural Networks (QNNs) --- neural networks with extremely low precision (e.g., 1-bit) weights and activations, at run-time. At train-time the quantized weights and activations are used for computing ...
OPENALEX
Open Access
DOI: https://doi.org/10.48550/arxiv.1609.07061
Aditya Malte, Pratik Ratadiya • arXiv (Cornell University)
(2019)
In this paper, we present a study of the recent advancements which have helped bring Transfer Learning to NLP through the use of semi-supervised training. We discuss cutting-edge methods and architectures such as BERT, GPT, ELMo, ULMFit amo...
OPENALEX
Open Access
DOI: https://doi.org/10.48550/arxiv.1910.07370
Sebastian Ruder, Matthew E. Peters, Swabha Swayamdipta, Thomas Wolf (2019)
The classic supervised machine learning paradigm is based on learning in isolation, a single predictive model for a task using a single dataset. This approach requires a large number of training examples and performs best for well-defined a...
OPENALEX
cc-by
DOI: https://doi.org/10.18653/v1/n19-5004
Muhammad Salihin Saealal, Mohd Zamri Ibrahim, David. J. Mulvaney, Mohd Ibrahim Shapiai et al. • PLoS ONE
(2022)
Deep learning is notably successful in data analysis, computer vision, and human control. Nevertheless, this approach has inevitably allowed the development of DeepFake video sequences and images that could be altered so that the changes ar...
DOAJ
Open Access (DOAJ)
Neofytos Dimitriou, Ognjen Arandjelović • Information
(2022)
Normalization as a layer within neural networks has over the years demonstrated its effectiveness in neural network optimization across a wide range of different tasks, with one of the most successful approaches being that of batch normaliz...
DOAJ
Open Access (DOAJ)
DOI: 10.3390/info13070337
Lu Yuan, Dongdong Chen, Yi‐Ling Chen, Noel Codella et al. • arXiv (Cornell University)
(2021)
Automated visual understanding of our diverse and open world demands computer vision models to generalize well with minimal customization for specific tasks, similar to human vision. Computer vision foundation models, which are trained on d...
OPENALEX
Open Access
DOI: https://doi.org/10.48550/arxiv.2111.11432
Dan Wu, Yanzhi Wang, Yuqi Fei, Guowang Gao • IEEE Access
(2025)
Model size and inference speed have brought about major challenges for the deployment of Convolutional Neural Networks (CNNs) in many applications. An effective approach to address this issue is model quantization, which achieves network co...
DOAJ
Open Access (DOAJ)
DOI: 10.1109/ACCESS.2025.3551802
Vinodkumar Patil, Manisha Patil, Smital Patil, Satish Desale • Advances in Engineering and Intelligence Systems
(2026)
Accurate detection of brain tumors at early stages is crucial for clinical diagnosis and treatment planning. Magnetic Resonance Imaging (MRI) is the most popular method due to its soft-tissue contrast and spatial resolution. However, manual...
DOAJ
Open Access (DOAJ)
DOI: 10.22034/aeis.2026.570662.1424
Faisal Mehmood, Shabir Ahmad, Taeg Keun Whangbo • Mathematics
(2023)
Deep learning is a sub-branch of artificial intelligence that acquires knowledge by training a neural network. It has many applications in the field of banking, automobile industry, agriculture, and healthcare industry. Deep learning has pl...
DOAJ
Open Access (DOAJ)
DOI: 10.3390/math11061360
Vladyslav Yavtukhovskyi, Violeta Tretynyk • Кібернетика та комп'ютерні технології
(2025)
Introduction. Convolutional neural networks (CNNs) are a subtype of neural networks developed specifically to work with images [1]. They have achieved great success both in research and in practical applications in recent years, however, on...
DOAJ
Open Access (DOAJ)
DOI: 10.34229/2707-451X.25.2.6
RT Pramod, Michael A Cohen, Joshua B Tenenbaum, Nancy Kanwisher • eLife
(2022)
Successful engagement with the world requires the ability to predict what will happen next. Here, we investigate how the brain makes a fundamental prediction about the physical world: whether the situation in front of us is stable, and henc...
DOAJ
Open Access (DOAJ)
DOI: 10.7554/eLife.71736
Yaoda Xu, Maryam Vaziri-Pashkam • NeuroImage
(2022)
Forming transformation-tolerant object representations is critical to high-level primate vision. Despite its significance, many details of tolerance in the human brain remain unknown. Likewise, despite the ability of convolutional neural ne...
DOAJ
Open Access (DOAJ)
DOI: 10.1016/j.neuroimage.2022.119635
Konstantinos Keremis, Eleni Vrochidou, George A. Papakostas • Journal of Imaging
(2025)
The ability of deep learning models to maintain consistent performance under image transformations-termed invariances, is critical for reliable deployment across diverse computer vision applications. This study presents a comprehensive empi...
DOAJ
Open Access (DOAJ)
DOI: 10.3390/jimaging11090322
Yihan Chen, Xingyu Gu, Zhen Liu, Jia Liang • Remote Sensing
(2022)
Traditional automatic pavement distress detection methods using convolutional neural networks (CNNs) require a great deal of time and resources for computing and are poor in terms of interpretability. Therefore, inspired by the successful a...
DOAJ
Open Access (DOAJ)
DOI: 10.3390/rs14081877
Gary Marcus • arXiv (Cornell University)
(2018)
Although deep learning has historical roots going back decades, neither the term "deep learning" nor the approach was popular just over five years ago, when the field was reignited by papers such as Krizhevsky, Sutskever and Hinton's now cl...
OPENALEX
Open Access
DOI: https://doi.org/10.48550/arxiv.1801.00631