Model complexity of deep learning: A survey

X Hu, L Chu, J Pei, W Liu, J Bian - Knowledge and Information Systems, 2021 - Springer
Abstract Model complexity is a fundamental problem in deep learning. In this paper, we
conduct a systematic overview of the latest studies on model complexity in deep learning …

Probabilistic machine learning and artificial intelligence

Z Ghahramani - Nature, 2015 - nature.com
How can a machine learn from experience? Probabilistic modelling provides a framework
for understanding what learning is, and has therefore emerged as one of the principal …

Sparsity in deep learning: Pruning and growth for efficient inference and training in neural networks

T Hoefler, D Alistarh, T Ben-Nun, N Dryden… - Journal of Machine …, 2021 - jmlr.org
The growing energy and performance costs of deep learning have driven the community to
reduce the size of neural networks by selectively pruning components. Similarly to their …

Bayesian deep learning and a probabilistic perspective of generalization

AG Wilson, P Izmailov - Advances in neural information …, 2020 - proceedings.neurips.cc
The key distinguishing property of a Bayesian approach is marginalization, rather than using
a single setting of weights. Bayesian marginalization can particularly improve the accuracy …

Hidden physics models: Machine learning of nonlinear partial differential equations

M Raissi, GE Karniadakis - Journal of Computational Physics, 2018 - Elsevier
While there is currently a lot of enthusiasm about “big data”, useful data is usually “small”
and expensive to acquire. In this paper, we present a new paradigm of learning partial …

[图书][B] Mathematics for machine learning

MP Deisenroth, AA Faisal, CS Ong - 2020 - books.google.com
The fundamental mathematical tools needed to understand machine learning include linear
algebra, analytic geometry, matrix decompositions, vector calculus, optimization, probability …

Sensitivity and generalization in neural networks: an empirical study

R Novak, Y Bahri, DA Abolafia, J Pennington… - arXiv preprint arXiv …, 2018 - arxiv.org
In practice it is often found that large over-parameterized neural networks generalize better
than their smaller counterparts, an observation that appears to conflict with classical notions …

Machine learning of linear differential equations using Gaussian processes

M Raissi, P Perdikaris, GE Karniadakis - Journal of Computational Physics, 2017 - Elsevier
This work leverages recent advances in probabilistic machine learning to discover
governing equations expressed by parametric linear operators. Such equations involve, but …

Deep kernel learning

AG Wilson, Z Hu, R Salakhutdinov… - Artificial intelligence …, 2016 - proceedings.mlr.press
We introduce scalable deep kernels, which combine the structural properties of deep
learning architectures with the non-parametric flexibility of kernel methods. Specifically, we …

Constrained Bayesian optimization for automatic chemical design using variational autoencoders

RR Griffiths, JM Hernández-Lobato - Chemical science, 2020 - pubs.rsc.org
Automatic Chemical Design is a framework for generating novel molecules with optimized
properties. The original scheme, featuring Bayesian optimization over the latent space of a …