Shufflenet v2: Practical guidelines for efficient cnn architecture design

N Ma, X Zhang, HT Zheng… - Proceedings of the …, 2018 - openaccess.thecvf.com
Current network architecture design is mostly guided by the indirect metric of computation
complexity, ie, FLOPs. However, the direct metric, such as speed, also depends on the other …

Deep learning in electron microscopy

JM Ede - Machine Learning: Science and Technology, 2021 - iopscience.iop.org
Deep learning is transforming most areas of science and technology, including electron
microscopy. This review paper offers a practical perspective aimed at developers with …

Revisiting small batch training for deep neural networks

D Masters, C Luschi - arxiv preprint arxiv:1804.07612, 2018 - arxiv.org
Modern deep neural network training is typically based on mini-batch stochastic gradient
optimization. While the use of large mini-batches increases the available computational …

Train longer, generalize better: closing the generalization gap in large batch training of neural networks

E Hoffer, I Hubara, D Soudry - Advances in neural …, 2017 - proceedings.neurips.cc
Background: Deep learning models are typically trained using stochastic gradient descent or
one of its variants. These methods update the weights using their gradient, estimated from a …

On large-batch training for deep learning: Generalization gap and sharp minima

NS Keskar, D Mudigere, J Nocedal… - arxiv preprint arxiv …, 2016 - arxiv.org
The stochastic gradient descent (SGD) method and its variants are algorithms of choice for
many Deep Learning tasks. These methods operate in a small-batch regime wherein a …

Deepchain: Auditable and privacy-preserving deep learning with blockchain-based incentive

J Weng, J Weng, J Zhang, M Li… - IEEE Transactions on …, 2019 - ieeexplore.ieee.org
Deep learning can achieve higher accuracy than traditional machine learning algorithms in
a variety of machine learning tasks. Recently, privacy-preserving deep learning has drawn …

Revisiting distributed synchronous SGD

J Chen, X Pan, R Monga, S Bengio… - arxiv preprint arxiv …, 2016 - arxiv.org
Distributed training of deep learning models on large-scale training data is typically
conducted with asynchronous stochastic optimization to maximize the rate of updates, at the …

Imagenet training in minutes

Y You, Z Zhang, CJ Hsieh, J Demmel… - Proceedings of the 47th …, 2018 - dl.acm.org
In this paper, we investigate large scale computers' capability of speeding up deep neural
networks (DNN) training. Our approach is to use large batch size, powered by the Layer …

Predicting disruptive instabilities in controlled fusion plasmas through deep learning

J Kates-Harbeck, A Svyatkovskiy, W Tang - Nature, 2019 - nature.com
Nuclear fusion power delivered by magnetic-confinement tokamak reactors holds the
promise of sustainable and clean energy. The avoidance of large-scale plasma instabilities …

An exhaustive survey on p4 programmable data plane switches: Taxonomy, applications, challenges, and future trends

EF Kfoury, J Crichigno, E Bou-Harb - IEEE access, 2021 - ieeexplore.ieee.org
Traditionally, the data plane has been designed with fixed functions to forward packets using
a small set of protocols. This closed-design paradigm has limited the capability of the …