Pascal Vincent
110 works · 26,047 citations · h-index 46
Top works
- Extracting and composing robust features with denoising autoencoders
- Representation Learning: A Review and New Perspectives
- Stacked Denoising Autoencoders: Learning Useful Representations in a Deep Network with a Local Denoising Criterion
- Why Does Unsupervised Pre-training Help Deep Learning?
- A Neural Probabilistic Language Model
- Static Analysis of Shape in TensorFlow Programs
- The Difficulty of Training Deep Architectures and the Effect of Unsupervised Pre-Training
- Modeling Temporal Dependencies in High-Dimensional Sequences: Application to Polyphonic Music Generation and Transcription
- Contractive Auto-Encoders: Explicit Invariance During Feature Extraction
- Out-of-Sample Extensions for LLE, Isomap, MDS, Eigenmaps, and Spectral Clustering
- Convex Neural Networks
- Audio Chord Recognition With Recurrent Neural Networks.
- A Connection Between Score Matching and Denoising Autoencoders
- Learning Eigenfunctions Links Spectral Embedding and Kernel PCA
- Generalized Denoising Auto-Encoders as Generative Models
- Unsupervised Feature Learning and Deep Learning: A Review and New Perspectives
- Quickly Generating Representative Samples from an RBM-Derived Process
- The Need for Open Source Software in Machine Learning
- Higher Order Contractive Auto-Encoder
- Adding noise to the input of a model trained with a regularized objective