PhD thesis: Modeles connexionnistes de l'apprentissage (connectionist learning models)

By Yann LeCun. 1987

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

Optimal Brain Damage (1989, methodology): “A time-honored (albeit inexact) measure of complexity is simply the number of non-zero free parameters, which is the measure we choose to use in this paper [but see (Denker, Le Cun and Solla, 1990)].”
A Survey on Bayesian Deep Learning (2016, background): “The idea of autoencoders has been around for decades [10, 29, 43, 63] and abundant variants of autoencoders have been proposed to enhance representation learning including sparse AE [88], contrastive AE [93], and denoising AE [111].”
Data Augmentation techniques in time series domain: a survey and taxonomy (2022, methodology): “GANs are certainly not the earliest generative architecture ever introduced; already in 1987 Yann Lecun [4] suggested in his thesis the Autoencoder (AE) architectures, which were capable of generating data modifications received as input.”
Ieee Transactions on Knowledge and Data Engineering 1 towards Bayesian Deep Learning: a Framework and Some Existing Methods (unknown): “The idea of autoencoders has been around for decades [10], [20], [35] and abundant variants of autoencoders have been proposed to enhance representation learning including sparse AE [48], contractive AE [51], and denoising AE [59].”
Forward Models: Supervised Learning with a Distal Teacher (1992, methodology): “This formulation is based on variational calculus and is closely allied with methods in optimal control theory (Kirk, 1970; LeCun, 1987).”
Adaptively Connected Neural Networks (2019, methodology): “The first type is the multi-layer perceptron (MLP), which first became popular and effective via the development of the backpropagation training algorithm [34, 17].”
Links between perceptrons, MLPs and SVMs (2004, methodology): “The (cid:12)rst one is the Multi-Layer Perceptron (MLP), which became useful with the introduction of the back-propagation training algorithm (LeCun, 1987; Rumelhart et al., 1986).”
Towards Bayesian Deep Learning: A Survey (2016, background): “The idea of autoencoders has been around for decades [8], [18], [25], [33] and abundant variants of autoencoders have been proposed to enhance representation learning including sparse AE [43], contrastive AE [46], and denoising AE [54].”