Credit assignment techniques in stochastic computation graphs

T Weber, N Heess, L Buesing… - The 22nd International …, 2019 - proceedings.mlr.press
Stochastic computation graphs (SCGs) provide a formalism to represent structured
optimization problems arising in artificial intelligence, including supervised, unsupervised …

Storchastic: A framework for general stochastic automatic differentiation

E Krieken, J Tomczak… - Advances in Neural …, 2021 - proceedings.neurips.cc
Modelers use automatic differentiation (AD) of computation graphs to implement complex
Deep Learning models without defining gradient computations. Stochastic AD extends AD to …

Optimisation in Neurosymbolic Learning Systems

E van Krieken - arXiv preprint arXiv:2401.10819, 2024 - arxiv.org
Neurosymbolic AI aims to integrate deep learning with symbolic AI. This integration has
many promises, such as decreasing the amount of data required to train a neural network …

Hulu video recommendation: from relevance to reasoning

X Xu, L Chen, S Zu, H Zhou - Proceedings of the 12th ACM Conference …, 2018 - dl.acm.org
Online Video Streaming services such as Hulu hosts tens of millions of premium videos,
which requires an effective recommendation system to help viewers discover what they …

Front contribution instead of back propagation

S Mishra, A Arunkumar - arXiv preprint arXiv:2106.05569, 2021 - arxiv.org
Deep Learning's outstanding track record across several domains has stemmed from the
use of error backpropagation (BP). Several studies, however, have shown that it is …