10.9k citations
- Centre National de la Recherche ScientifiqueFR750 papers
- McGill UniversityCA629 papers
- Université Paris CitéFR606 papers
- University of British ColumbiaCA605 papers
- University of TorontoCA602 papers
- University of California, Santa CruzUS590 papers
- University of VictoriaCA588 papers
- University of ArizonaUS577 papers
- University of GenevaCH573 papers
- University College LondonGB551 papers
- University of CambridgeGB551 papers
- University of ChicagoUS549 papers
4 papers · 2 filters
Big Neural Networks Waste Capacity
Yann N. Dauphin, Yoshua Bengio
This article exposes the failure of some big neural networks to leverage added capacity to reduce underfitting. Past research suggest diminishing returns when increasing the size o…
Metric-Free Natural Gradient for Joint-Training of Boltzmann Machines
Guillaume Desjardins, Razvan Pascanu, Aaron Courville +1
This paper introduces the Metric-Free Natural Gradient (MFNG) algorithm for training Boltzmann Machines. Similar in spirit to the Hessian-Free method of Martens [8], our algorithm…
A Semantic Matching Energy Function for Learning with Multi-relational Data
Xavier Glorot, Antoine Bordes, Jason Weston +1
Large-scale relational learning becomes crucial for handling the huge amounts of structured data generated daily in many application domains ranging from computational biology or i…
Feature grouping from spatially constrained multiplicative interaction
Felix Bauer, Roland Memisevic
We present a feature learning model that learns to encode relationships between images. The model is defined as a Gated Boltzmann Machine, which is constrained such that hidden uni…