Backpropagation: theory, architectures, and applications

By Yves Chauvin, David E. Rumelhart. 1995

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Hacking smart machines with smarter ones: How to extract meaningful data from machine learning classifiers (2013, methodology): “The precision and recall summary of the meta-classiﬁer Table 6 summarizes the experiment results: with respect to the Google class, we achieve a precision of 0.954 and a recall of 0.932.”
Deep Learning for IoT Big Data and Streaming Analytics: A Survey (2017, background): “The error rate is propagated back across the network to the input layer (known as backpropagation algorithm [35], [36]).”
Deep UQ: Learning deep neural network surrogate models for high dimensional uncertainty quantification (2018, methodology): “ctions. To perform gradient descent optimization one needs access to the gradients of the objective function. For training DNNs, this is achieved by utilizing the celebrated backpropagation algorithm [63]. In essence, the backpropagation algorithm is a recursive application of the standard chain rul”
TI-POOLING: Transformation-Invariant Pooling for Feature Learning in Convolutional Neural Networks (2016, methodology): “Therefore, we have all the building blocks for a back-propagation parameter optimization [6], which concludes the description of TI-POOLING and of the proposed topology.”
DATA MINING TECHNIQUES (2003, background): “25, 47, 48], neural networks [7, 20, 68], and so on.”
Self-Adaptive Physics-Informed Neural Networks using a Soft Attention Mechanism (2020, background): “The parameters θ are trained by back-propagation [16] on a loss function that penalizes the output for not satisfying (1)-(3): L(θ) = Lr(θ) + Lb(θ) + L0(θ) , (5) where Lr is the residual loss from 4 and, for initial and boundary value problems, Lub and Lu0 are the boundary and initial condition loss”
Evolving artificial neural networks (1999, background): “A detailed review of BP and other learning algorithms can be found in [7], [17], and [25].”
Simulator-free solution of high-dimensional stochastic elliptic partial diﬀerential equations using deep neural networks (2022, background): “, Tensorflow: large-scale machine learning on heterogeneous distributed systems (2016), CoRR [70] Chauvin, Y.”
An Approximation of the Error Backpropagation Algorithm in a Predictive Coding Network with Local Hebbian Synaptic Plasticity (2017, methodology): “Artificial neural networks (ANNs) employing backpropagation have been used extensively in machine learning (LeCun et al., 1989; Chauvin & Rumelhart, 1995; Bogacz, Markowska-Kaczmar, & Kozik, 1999) and have become particularly popular recently, with the newer deep networks having some spectacular…”
Simulator-free solution of high-dimensional stochastic elliptic partial differential equations using deep neural networks (2019, methodology): “o the spatial variables ‘x’ using automatic dierentiation (AD) [45]in TensorFlow [70].The exact gradient of the loss function needed for the ADAM update in Eq. (30) is obtained using backpropagation [71]. 15 3. Numerical examples In this section we demonstrate the performance of our method with two ”