Results 1  10
of
77
Visualizing data using tSNE
 Costsensitive Machine Learning for Information Retrieval 33
"... We present a new technique called “tSNE ” that visualizes highdimensional data by giving each datapoint a location in a two or threedimensional map. The technique is a variation of Stochastic Neighbor Embedding (Hinton and Roweis, 2002) that is much easier to optimize, and produces significantly ..."
Abstract

Cited by 92 (9 self)
 Add to MetaCart
We present a new technique called “tSNE ” that visualizes highdimensional data by giving each datapoint a location in a two or threedimensional map. The technique is a variation of Stochastic Neighbor Embedding (Hinton and Roweis, 2002) that is much easier to optimize, and produces significantly better visualizations by reducing the tendency to crowd points together in the center of the map. tSNE is better than existing techniques at creating a single map that reveals structure at many different scales. This is particularly important for highdimensional data that lie on several different, but related, lowdimensional manifolds, such as images of objects from multiple classes seen from multiple viewpoints. For visualizing the structure of very large data sets, we show how tSNE can use random walks on neighborhood graphs to allow the implicit structure of all of the data to influence the way in which a subset of the data is displayed. We illustrate the performance of tSNE on a wide variety of data sets and compare it with many other nonparametric visualization techniques, including Sammon mapping, Isomap, and Locally Linear Embedding. The visualizations produced by tSNE are significantly better than those produced by the other techniques on almost all of the data sets.
Extracting and Composing Robust Features with Denoising Autoencoders
, 2008
"... Previous work has shown that the difficulties in learning deep generative or discriminative models can be overcome by an initial unsupervised learning step that maps inputs to useful intermediate representations. We introduce and motivate a new training principle for unsupervised learning of a repre ..."
Abstract

Cited by 81 (15 self)
 Add to MetaCart
Previous work has shown that the difficulties in learning deep generative or discriminative models can be overcome by an initial unsupervised learning step that maps inputs to useful intermediate representations. We introduce and motivate a new training principle for unsupervised learning of a representation based on the idea of making the learned representations robust to partial corruption of the input pattern. This approach can be used to train autoencoders, and these denoising autoencoders can be stacked to initialize deep architectures. The algorithm can be motivated from a manifold learning and information theoretic perspective or from a generative model perspective. Comparative experiments clearly show the surprising advantage of corrupting the input of autoencoders on a pattern classification benchmark suite.
Curriculum Learning
"... Humans and animals learn much better when the examples are not randomly presented but organized in a meaningful order which illustrates gradually more concepts, and gradually more complex ones. Here, we formalize such training strategies in the context of machine learning, and call them “curriculum ..."
Abstract

Cited by 49 (6 self)
 Add to MetaCart
Humans and animals learn much better when the examples are not randomly presented but organized in a meaningful order which illustrates gradually more concepts, and gradually more complex ones. Here, we formalize such training strategies in the context of machine learning, and call them “curriculum learning”. In the context of recent research studying the difficulty of training in the presence of nonconvex training criteria (for deep deterministic and stochastic neural networks), we explore curriculum learning in various setups. The experiments show that significant improvements in generalization can be achieved. We hypothesize that curriculum learning has both an effect on the speed of convergence of the training process to a minimum and, in the case of nonconvex criteria, on the quality of the local minima obtained: curriculum learning can be seen as a particular form of continuation method (a general strategy for global optimization of nonconvex functions). 1.
Exploring strategies for training deep neural networks
 Journal of Machine Learning Research
"... Département d’informatique et de recherche opérationnelle ..."
Abstract

Cited by 42 (8 self)
 Add to MetaCart
Département d’informatique et de recherche opérationnelle
Bayesian nonparametric latent feature models
 In Bayesian Statistics 8
, 2007
"... We are often interested in explaining data through a set of hidden factors or features. When the number of hidden features is unknown, the Indian Buffet Process (IBP) is a nonparametric latent feature model that does not bound the number of active features in dataset. However, the IBP assumes that a ..."
Abstract

Cited by 37 (4 self)
 Add to MetaCart
We are often interested in explaining data through a set of hidden factors or features. When the number of hidden features is unknown, the Indian Buffet Process (IBP) is a nonparametric latent feature model that does not bound the number of active features in dataset. However, the IBP assumes that all latent features are uncorrelated, making it inadequate for many realworld problems. We introduce a framework for correlated nonparametric feature models, generalising the IBP. We use this framework to generate several specific models and demonstrate applications on realworld datasets. 1
Domain adaptation for largescale sentiment classification: A deep learning approach
 In Proceedings of the Twentyeight International Conference on Machine Learning, ICML
, 2011
"... The exponential increase in the availability of online reviews and recommendations makes sentiment classification an interesting topic in academic and industrial research. Reviews can span so many different domains that it is difficult to gather annotated training data for all of them. Hence, this p ..."
Abstract

Cited by 24 (2 self)
 Add to MetaCart
The exponential increase in the availability of online reviews and recommendations makes sentiment classification an interesting topic in academic and industrial research. Reviews can span so many different domains that it is difficult to gather annotated training data for all of them. Hence, this paper studies the problem of domain adaptation for sentiment classifiers, hereby a system is trained on labeled reviews from one source domain but is meant to be deployed on another. We propose a deep learning approach which learns to extract a meaningful representation for each review in an unsupervised fashion. Sentiment classifiers trained with this highlevel feature representation clearly outperform stateoftheart methods on a benchmark composed of reviews of 4 types of Amazon products. Furthermore, this method scales well and allowed us to successfully perform domain adaptation on a larger industrialstrength dataset of 22 domains. 1.
Tiled convolutional neural networks
 In NIPS, in press
, 2010
"... Convolutional neural networks (CNNs) have been successfully applied to many tasks such as digit and object recognition. Using convolutional (tied) weights significantly reduces the number of parameters that have to be learned, and also allows translational invariance to be hardcoded into the archit ..."
Abstract

Cited by 22 (6 self)
 Add to MetaCart
Convolutional neural networks (CNNs) have been successfully applied to many tasks such as digit and object recognition. Using convolutional (tied) weights significantly reduces the number of parameters that have to be learned, and also allows translational invariance to be hardcoded into the architecture. In this paper, we consider the problem of learning invariances, rather than relying on hardcoding. We propose tiled convolution neural networks (Tiled CNNs), which use a regular “tiled ” pattern of tied weights that does not require that adjacent hidden units share identical weights, but instead requires only that hidden units k steps away from each other to have tied weights. By pooling over neighboring units, this architecture is able to learn complex invariances (such as scale and rotational invariance) beyond translational invariance. Further, it also enjoys much of CNNs’ advantage of having a relatively small number of learned parameters (such as ease of learning and greater scalability). We provide an efficient learning algorithm for Tiled CNNs based on Topographic ICA, and show that learning complex invariant features allows us to achieve highly competitive results for both the NORB and CIFAR10 datasets. 1
SumProduct Networks: A New Deep Architecture
"... The key limiting factor in graphical model inference and learning is the complexity of the partition function. We thus ask the question: what are general conditions under which the partition function is tractable? The answer leads to a new kind of deep architecture, which we call sumproduct networks ..."
Abstract

Cited by 21 (4 self)
 Add to MetaCart
The key limiting factor in graphical model inference and learning is the complexity of the partition function. We thus ask the question: what are general conditions under which the partition function is tractable? The answer leads to a new kind of deep architecture, which we call sumproduct networks (SPNs). SPNs are directed acyclic graphs with variables as leaves, sums and products as internal nodes, and weighted edges. We show that if an SPN is complete and consistent it represents the partition function and all marginals of some graphical model, and give semantics to its nodes. Essentially all tractable graphical models can be cast as SPNs, but SPNs are also strictly more general. We then propose learning algorithms for SPNs, based on backpropagation and EM. Experiments show that inference and learning with SPNs can be both faster and more accurate than with standard deep networks. For example, SPNs perform image completion better than stateoftheart deep networks for this task. SPNs also have intriguing potential connections to the architecture of the cortex. 1
On Optimization Methods for Deep Learning
"... The predominant methodology in training deep learning advocates the use of stochastic gradient descent methods (SGDs). Despite its ease of implementation, SGDs are difficult to tune and parallelize. These problems make it challenging to develop, debug and scale up deep learning algorithms with SGDs. ..."
Abstract

Cited by 19 (5 self)
 Add to MetaCart
The predominant methodology in training deep learning advocates the use of stochastic gradient descent methods (SGDs). Despite its ease of implementation, SGDs are difficult to tune and parallelize. These problems make it challenging to develop, debug and scale up deep learning algorithms with SGDs. In this paper, we show that more sophisticated offtheshelf optimization methods such as Limited memory BFGS (LBFGS) and Conjugate gradient (CG) with line search can significantly simplify and speed up the process of pretraining deep algorithms. In our experiments, the difference between LBFGS/CG and SGDs are more pronounced if we consider algorithmic extensions (e.g., sparsity regularization) and hardware extensions (e.g., GPUs or computer clusters). Our experiments with distributed optimization support the use of LBFGS with locally connected networks and convolutional neural networks. Using LBFGS, our convolutional network model achieves 0.69 % on the standard MNIST dataset. This is a stateoftheart result on MNIST among algorithms that do not use distortions or pretraining. 1.
Dimensionality Reduction: A Comparative Review
, 2008
"... In recent years, a variety of nonlinear dimensionality reduction techniques have been proposed, many of which rely on the evaluation of local properties of the data. The paper presents a review and systematic comparison of these techniques. The performances of the techniques are investigated on arti ..."
Abstract

Cited by 19 (0 self)
 Add to MetaCart
In recent years, a variety of nonlinear dimensionality reduction techniques have been proposed, many of which rely on the evaluation of local properties of the data. The paper presents a review and systematic comparison of these techniques. The performances of the techniques are investigated on artificial and natural tasks. The results of the experiments reveal that nonlinear techniques perform well on selected artificial tasks, but do not outperform the traditional PCA on realworld tasks. The paper explains these results by identifying weaknesses of current nonlinear techniques, and suggests how the performance of nonlinear dimensionality reduction techniques may be improved.