We attack the problem of recognizing digits in a real application using unsupervised feature learning methods: reading house numbers from street level photos.Expand
In this paper, we show that several simple factors, such as the number of hidden nodes in the model, may be more important to achieving high performance than the learning algorithm or the depth of the model.Expand
We show that an end-to-end deep learning approach can be used to recognize either English or Mandarin Chinese speech-two vastly different languages.Expand
We present a state-of-the-art speech recognition system developed using end-to-end deep learning, that can surpass more complicated traditional methods.Expand
Proceedings of the 21st International Conferenceā¦
1 November 2012
TLDR
In this paper, we take a different route and combine the representational power of large, multilayer neural networks together with recent developments in unsupervised feature learning, which allows us to use a common framework to train highly-accurate text detector and character recognizer modules.Expand
We investigate the reasons for the success of sparse coding over VQ by decoupling these phases, allowing us to separate out the contributions of training and encoding in controlled way.Expand
We present an alternative approach to training extremely large neural networks that leverages inexpensive computing power in the form of GPUs and introduces the use of high-speed communications infrastructure to tightly coordinate distributed gradient computations.Expand
This chapter will summarize recent results and technical tricks that are needed to make effective use of K-means clustering for learning large scale representations of images.Expand
We show that more sophisticated off-the-shelf optimization methods such as Limited memory BFGS (L-BFGS) and Conjugate gradient (CG) with line search can significantly simplify and speed up the process of pretraining deep algorithms.Expand