--- a/writeup/aigaion-shorter.bib	Sun Oct 31 22:40:33 2010 -0400
+++ b/writeup/aigaion-shorter.bib	Mon Nov 22 14:52:33 2010 -0500
@@ -1,5 +1,99 @@
 %Aigaion2 BibTeX export from LISA - Publications
-%Tuesday 01 June 2010 10:46:52 AM
+%Tuesday 02 November 2010 04:10:50 PM
+@MASTERSTHESIS{,
+    author = {Breuleux, Olivier},
+     title = {{\'{E}}chantillonnage dynamique de champs markoviens},
+      year = {2010},
+    school = {Universit{\'{e}} de Montr{\'{e}}al}
+}
+
+@PHDTHESIS{,
+    author = {Rivest, Fran{\c c}ois},
+     title = {Mod{\`{e}}le informatique du coapprentissage des ganglions de la base et du cortex : L’apprentissage par renforcement et le d{\'{e}}veloppement de repr{\'{e}}sentations},
+      year = {2009},
+    school = {Universit{\'{e}} de Montr{\'{e}}al, D{\'{e}}partement d’informatique et de recherche op{\'{e}}rationnelle},
+  abstract = {English follow:
+
+Tout au long de la vie, le cerveau d{\'{e}}veloppe des repr{\'{e}}sentations de son
+environnement permettant {\`{a}} l’individu d’en tirer meilleur profit. Comment ces
+repr{\'{e}}sentations se d{\'{e}}veloppent-elles pendant la qu{\^{e}}te de r{\'{e}}compenses demeure un
+myst{\`{e}}re. Il est raisonnable de penser que le cortex est le si{\`{e}}ge de ces repr{\'{e}}sentations
+et que les ganglions de la base jouent un r{\^{o}}le important dans la maximisation des
+r{\'{e}}compenses. En particulier, les neurones dopaminergiques semblent coder un signal
+d’erreur de pr{\'{e}}diction de r{\'{e}}compense. Cette th{\`{e}}se {\'{e}}tudie le probl{\`{e}}me en construisant,
+{\`{a}} l’aide de l’apprentissage machine, un mod{\`{e}}le informatique int{\'{e}}grant de nombreuses
+{\'{e}}vidences neurologiques.
+        Apr{\`{e}}s une introduction au cadre math{\'{e}}matique et {\`{a}} quelques algorithmes de
+l’apprentissage machine, un survol de l’apprentissage en psychologie et en
+neuroscience et une revue des mod{\`{e}}les de l’apprentissage dans les ganglions de la
+base, la th{\`{e}}se comporte trois articles. Le premier montre qu’il est possible
+d’apprendre {\`{a}} maximiser ses r{\'{e}}compenses tout en d{\'{e}}veloppant de meilleures
+repr{\'{e}}sentations des entr{\'{e}}es. Le second article porte sur l'important probl{\`{e}}me toujours
+non r{\'{e}}solu de la repr{\'{e}}sentation du temps. Il d{\'{e}}montre qu’une repr{\'{e}}sentation du temps
+peut {\^{e}}tre acquise automatiquement dans un r{\'{e}}seau de neurones artificiels faisant
+office de m{\'{e}}moire de travail. La repr{\'{e}}sentation d{\'{e}}velopp{\'{e}}e par le mod{\`{e}}le ressemble
+beaucoup {\`{a}} l’activit{\'{e}} de neurones corticaux dans des t{\^{a}}ches similaires. De plus, le
+mod{\`{e}}le montre que l’utilisation du signal d’erreur de r{\'{e}}compense peut acc{\'{e}}l{\'{e}}rer la
+construction de ces repr{\'{e}}sentations temporelles. Finalement, il montre qu’une telle
+repr{\'{e}}sentation acquise automatiquement dans le cortex peut fournir l’information
+n{\'{e}}cessaire aux ganglions de la base pour expliquer le signal dopaminergique. Enfin,
+le troisi{\`{e}}me article {\'{e}}value le pouvoir explicatif et pr{\'{e}}dictif du mod{\`{e}}le sur diff{\'{e}}rentes
+situations comme la pr{\'{e}}sence ou l’absence d’un stimulus (conditionnement classique
+ou de trace) pendant l’attente de la r{\'{e}}compense. En plus de faire des pr{\'{e}}dictions tr{\`{e}}s
+int{\'{e}}ressantes en lien avec la litt{\'{e}}rature sur les intervalles de temps, l’article r{\'{e}}v{\`{e}}le
+certaines lacunes du mod{\`{e}}le qui devront {\^{e}}tre am{\'{e}}lior{\'{e}}es.
+       Bref, cette th{\`{e}}se {\'{e}}tend les mod{\`{e}}les actuels de l’apprentissage des ganglions de
+la base et du syst{\`{e}}me dopaminergique au d{\'{e}}veloppement concurrent de
+repr{\'{e}}sentations temporelles dans le cortex et aux interactions de ces deux structures.
+
+        Throughout lifetime, the brain develops abstract representations of its
+environment that allow the individual to maximize his benefits. How these
+representations are developed while trying to acquire rewards remains a mystery. It is
+reasonable to assume that these representations arise in the cortex and that the basal
+ganglia are playing an important role in reward maximization. In particular,
+dopaminergic neurons appear to code a reward prediction error signal. This thesis
+studies the problem by constructing, using machine learning tools, a computational
+model that incorporates a number of relevant neurophysiological findings.
+        After an introduction to the machine learning framework and to some of its
+algorithms, an overview of learning in psychology and neuroscience, and a review of
+models of learning in the basal ganglia, the thesis comprises three papers. The first
+article shows that it is possible to learn a better representation of the inputs while
+learning to maximize reward. The second paper addresses the important and still
+unresolved problem of the representation of time in the brain. The paper shows that a
+time representation can be acquired automatically in an artificial neural network
+acting like a working memory. The representation learned by the model closely
+resembles the activity of cortical neurons in similar tasks. Moreover, the model shows
+that the reward prediction error signal could accelerate the development of the
+temporal representation. Finally, it shows that if such a learned representation exists
+in the cortex, it could provide the necessary information to the basal ganglia to
+explain the dopaminergic signal. The third article evaluates the explanatory and
+predictive power of the model on the effects of differences in task conditions such as
+the presence or absence of a stimulus (classical versus trace conditioning) while
+waiting for the reward. Beyond making interesting predictions relevant to the timing
+literature, the paper reveals some shortcomings of the model that will need to be
+resolved.
+       In summary, this thesis extends current models of reinforcement learning of
+the basal ganglia and the dopaminergic system to the concurrent development of
+representation in the cortex and to the interactions between these two regions.}
+}
+
+@MASTERSTHESIS{,
+    author = {Wood, Sean},
+     title = {Non-negative matrix decomposition approaches to frequency domain analysis of music audio signals},
+      year = {2010},
+    school = {Universit{\'{e}} de Montr{\'{e}}al}
+}
+
+@TECHREPORT{ARXIV-2010,
+       author = {Bastien, Fr{\'{e}}d{\'{e}}ric and Bengio, Yoshua and Bergeron, Arnaud and Boulanger-Lewandowski, Nicolas and Breuel, Thomas and Chherawala, Youssouf and Cisse, Moustapha and C{\^{o}}t{\'{e}}, Myriam and Erhan, Dumitru and Eustache, Jeremy and Glorot, Xavier and Muller, Xavier and Pannetier Lebeuf, Sylvain and Pascanu, Razvan and Rifai, Salah and Savard, Fran{\c c}ois and Sicard, Guillaume},
+     keywords = {Computer Vision and Pattern Recognition, Learning, Neural and Evolutionary Computing},
+        title = {Deep Self-Taught Learning for Handwritten Character Recognition},
+       number = {1353},
+         year = {2010},
+  institution = {University of Montr{\'{e}}al},
+     abstract = {Recent theoretical and empirical work in statistical machine learning has demonstrated the importance of learning algorithms for deep architectures, i.e., function classes obtained by composing multiple non-linear transformations. Self-taught learning (exploiting unlabeled examples or examples from other distributions) has already been applied to deep learners, but mostly to show the advantage of unlabeled examples. Here we explore the advantage brought by {\em out-of-distribution examples}. For this purpose we developed a powerful generator of stochastic variations and noise processes for character images, including not only affine transformations but also slant, local elastic deformations, changes in thickness, background images, grey level changes, contrast, occlusion, and various types of noise. The out-of-distribution examples are obtained from these highly distorted images or by including examples of object classes different from those in the target test set. We show that {\em deep learners benefit more from out-of-distribution examples than a corresponding shallow learner}, at least in the area of handwritten character recognition. In fact, we show that they beat previously published results and reach human-level performance on both handwritten digit classification and 62-class handwritten character recognition.}
+}
+
 @INPROCEEDINGS{Attardi+al-2009,
      author = {Attardi, Giuseppe and Dell'Orletta, Felice and Simi, Maria and Turian, Joseph},
    keywords = {classifier, dependency parsing, natural language, parser, perceptron},
@@ -409,7 +503,7 @@
     volume = {5},
       year = {2004},
      pages = {1089--1105},
-  journal = {Journal of Machine Learning Research},
+  crossref = {JMLR-shorter},
   abstract = {Most machine learning researchers perform quantitative experiments to estimate generalization error and compare the performance of different algorithms (in particular, their proposed algorithm). In order to be able to draw statistically convincing conclusions, it is important to estimate the uncertainty of such estimates. This paper studies the very commonly used K-fold cross-validation estimator of generalization performance. The main theorem shows that there exists no universal (valid under all distributions) unbiased estimator of the variance of K-fold cross-validation. The analysis that accompanies this result is based on the eigen-decomposition of the covariance matrix of errors, which has only three different eigenvalues corresponding to three degrees of freedom of the matrix and three components of the total variance. This analysis helps to better understand the nature of the problem and how it can make naive estimators (that don’t take into account the error correlations due to the overlap between training and test sets) grossly underestimate variance. This is confirmed by numerical experiments in which the three components of the variance are compared when the difficulty of the learning problem and the number of folds are varied.},
 topics={Comparative},cat={J},
 }
@@ -1089,7 +1183,7 @@
     volume = {3},
       year = {2003},
      pages = {1137--1155},
-  journal = {Journal of Machine Learning Research},
+  crossref = {JMLR-shorter},
   abstract = {A goal of statistical language modeling is to learn the joint probability function of sequences of words in a language. This is intrinsically difficult because of the curse of dimensionality: a word sequence on which the model will be tested is likely to be different from all the word sequences seen during training. Traditional but very successful approaches based on n-grams obtain generalization by concatenating very short overlapping sequences seen in the training set. We propose to fight the curse of dimensionality by learning a distributed representation for words which allows each training sentence to inform the model about an exponential number of semantically neighboring sentences. The model learns simultaneously (1) a distributed representation for each word along with (2) the probability function for word sequences, expressed in terms of these representations. Generalization is obtained because a sequence of words that has never been seen before gets high probability if it is made of words that are similar (in the sense of having a nearby representation) to words forming an already seen sentence. Training such large models (with millions of parameters) within a reasonable time is itself a significant challenge. We report on experiments using neural networks for the probability function, showing on two text corpora that the proposed approach significantly improves on state-of-the-art n-gram models, and that the proposed approach allows to take advantage of longer contexts.},
 topics={Markov,Unsupervised,Language},cat={J},
 }
@@ -1232,12 +1326,20 @@
     The advantage of quadratic units was strongest in conjunction with sparse and convolutional hidden units.}
 }
 
-@MISC{bergstra+al:2010-scipy,
-        author = {Bergstra, James},
-         title = {Optimized Symbolic Expressions and {GPU} Metaprogramming with Theano},
-          year = {2010},
-  howpublished = {{SciPy}},
-          note = {Oral}
+@ARTICLE{Bergstra+al-2010,
+    author = {Bergstra, James and Bengio, Yoshua and Louradour, Jerome},
+     title = {Suitability of V1 Energy Models for Object Classification},
+   journal = {Neural Computation},
+      year = {2010},
+      note = {to appear}
+}
+
+@INPROCEEDINGS{bergstra+al:2010-scipy,
+     author = {Bergstra, James and Breuleux, Olivier and Bastien, Fr{\'{e}}d{\'{e}}ric and Lamblin, Pascal and Pascanu, Razvan and Desjardins, Guillaume and Turian, Joseph and Bengio, Yoshua},
+      title = {Theano: a {CPU} and {GPU} Math Expression Compiler},
+  booktitle = {Proceedings of the Python for Scientific Computing Conference ({SciPy})},
+       year = {2010},
+       note = {Oral}
 }
 
 @MISC{bergstra+al:2010-sharcnet,
@@ -1257,10 +1359,13 @@
 }
 
 @INPROCEEDINGS{Bergstra+Bengio-2009,
-    author = {Bergstra, James and Bengio, Yoshua},
-     title = {Slow, Decorrelated Features for Pretraining Complex Cell-like Networks},
-      year = {2009},
-  crossref = {NIPS22}
+     author = {Bergstra, James and Bengio, Yoshua},
+      title = {Slow, Decorrelated Features for Pretraining Complex Cell-like Networks},
+       year = {2009},
+      pages = {99--107},
+  publisher = {MIT Press},
+        url = {http://books.nips.cc/papers/files/nips22/NIPS2009_0933.pdf},
+   crossref = {NIPS22}
 }
 
 @ARTICLE{bergstra+casagrande+erhan+eck+kegl:2006,
@@ -1279,8 +1384,10 @@
 @INPROCEEDINGS{bergstra+lacoste+eck:2006,
      author = {Bergstra, James and Lacoste, Alexandre and Eck, Douglas},
       title = {Predicting Genre Labels for Artists using FreeDB},
-  booktitle = {Proc. 7th International Conference on Music Information Retrieval (ISMIR)},
+  booktitle = {Proc. 7th International Conference on Music Information Retrieval ({ISMIR})},
        year = {2006},
+      pages = {85--88},
+  publisher = {University of Victoria},
 SOURCE = {OwnPublication},
   PDF = {papers/2006_ismir_freedb.pdf},
 }
@@ -1290,7 +1397,7 @@
       title = {Scalable Genre and Tag Prediction with Spectral Covariance},
   booktitle = {{ISMIR}},
        year = {2010},
-       note = {accepted}
+      pages = {507--512},
 }
 
 @MASTERSTHESIS{Bergstra-Msc-2006,
@@ -1391,7 +1498,7 @@
        year = {1997},
       pages = {490--494},
   publisher = {IEEE},
-        url = {http://www.iro.umontreal.ca/~lisa/pointeurs/bottou-lecun-bengio-97.ps.gz},
+        url = {http://www.iro.umontreal.ca/~lisa/pointeurs/bottou-lecun-bengio-97.pdf},
 topics={PriorKnowledge,Speech},cat={C},
 }
 
@@ -1431,6 +1538,15 @@
     school = {Universit{\'{e}} de Montr{\'{e}}al, D{\'{e}}partement d'Informatique et de Recherche Op{\'{e}}rationnel}
 }
 
+@TECHREPORT{Breuleux+al-TR-2010,
+       author = {Breuleux, Olivier and Bengio, Yoshua and Vincent, Pascal},
+        title = {Unlearning for Better Mixing},
+       number = {1349},
+         year = {2010},
+  institution = {Universit{\'{e}} de Montr{\'{e}}al/DIRO},
+     abstract = {Two learning algorithms were recently proposed – Herding and Fast Persistent Contrastive Divergence (FPCD) – which share the following interesting characteristic: they exploit changes in the model parameters while sampling in order to escape modes and mix better, during the sampling process that is part of the learning algorithm. We first justify such approaches as ways to escape modes while approximately keeping the same asymptotic distribution of the {Markov} chain. We then extend FPCD using an idea borrowed from Herding in order to obtain a pure sampling algorithm and show empirically that this FPCD-sampler yields substantially better samples than Gibbs sampling. Because these algorithms entangle the model and the sampling algorithm and we want to evaluate both (but particularly how well the sampling schemes mix), it is not always easy to evaluate them, so we propose a “black-box” approach based on how well and how quickly the samples generated by a model “cover” the test set examples. We empirically study these algorithms and variations with this perspective and these new evaluation tools in order to better understand their strengths and limitations.}
+}
+
 @INPROCEEDINGS{Carreau+Bengio-2007,
      author = {Carreau, Julie and Bengio, Yoshua},
       title = {A Hybrid {Pareto} Model for Conditional Density Estimation of Asymmetric Fat-Tail Data},
@@ -1444,7 +1560,7 @@
 
 @ARTICLE{Carreau+Bengio-2009,
     author = {Carreau, Julie and Bengio, Yoshua},
-     title = {A Hybrid {Pareto} Mixture for Conditional Asymmetric Fat-Tailed Distributio\ n},
+     title = {A Hybrid {Pareto} Mixture for Conditional Asymmetric Fat-Tailed Distribution},
    journal = {IEEE Transactions on Neural Networks},
     volume = {20},
     number = {7},
@@ -1569,7 +1685,7 @@
     author = {Bengio, Yoshua and Chapados, Nicolas},
      title = {Extensions to Metric-Based Model Selection},
       year = {2003},
-  journal = {Journal of Machine Learning Research},
+  crossref = {JMLR-shorter},
   abstract = {Metric-based methods have recently been introduced for model selection and regularization, often yielding very significant improvements over the alternatives tried (including cross-validation). All these methods require unlabeled data over which to compare functions and detect gross differences in behavior away from the training points. We introduce three new extensions of the metric model selection methods and apply them to feature selection. The first extension takes advantage of the particular case of time-series data in which the task involves prediction with a horizon h. The idea is to use at t the h unlabeled examples that precede t for model selection. The second extension takes advantage of the different error distributions of cross-validation and the metric methods: cross-validation tends to have a larger variance and is unbiased. A hybrid combining the two model selection methods is rarely beaten by any of the two methods. The third extension deals with the case when unlabeled data is not available at all, using an estimated input density. Experiments are described to study these extensions in the context of capacity control and feature subset selection.},
 topics={ModelSelection,Finance},cat={J},
 }
@@ -1789,10 +1905,10 @@
 @INPROCEEDINGS{Desjardins+al-2010,
      author = {Desjardins, Guillaume and Courville, Aaron and Bengio, Yoshua},
       title = {Tempered {Markov} Chain Monte Carlo for training of Restricted {Boltzmann} Machine},
-  booktitle = {Proceedings of AISTATS 2010},
+  booktitle = {JMLR W\&CP: Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics (AISTATS 2010)},
      volume = {9},
        year = {2010},
-      pages = {145-152},
+      pages = {145--152},
    abstract = {Alternating Gibbs sampling is the most common scheme used for sampling from Restricted {Boltzmann} Machines (RBM), a crucial component in deep architectures such as Deep Belief Networks. However, we find that it often does a very poor job of rendering the diversity of modes captured by the trained model. We suspect that this hinders the advantage that could in principle be brought by training algorithms relying on Gibbs sampling for uncovering spurious modes, such as the Persistent Contrastive Divergence algorithm. To alleviate this problem, we explore the use of tempered {Markov} Chain Monte-Carlo for sampling in RBMs. We find both through visualization of samples and measures of likelihood on a toy dataset that it helps both sampling and learning.}
 }
 
@@ -2255,7 +2371,7 @@
     volume = {11},
       year = {2010},
      pages = {625--660},
-  journal = {Journal of Machine Learning Research},
+  crossref = {JMLR-shorter},
   abstract = {Much recent research has been devoted to learning algorithms for deep architectures such as Deep Belief Networks and stacks of auto-encoder variants, with impressive results obtained in several areas, mostly on vision and language datasets. The best results obtained on supervised learning tasks involve an unsupervised learning component, usually in an unsupervised pre-training phase. Even though these new algorithms have enabled training deep models, many questions remain as to the nature of this difficult learning problem. The main question investigated here is the following: why does unsupervised pre-training work and why does it work so well? Answering these questions is important if learning in deep architectures is to be further improved. We propose several explanatory hypotheses and test them through extensive simulations. We empirically show the influence of pre-training with respect to architecture depth, model capacity, and number of training examples. The experiments confirm and clarify the advantage of unsupervised pre-training. The results suggest that unsupervised pre-training guides the learning towards basins of attraction of minima that are better in terms of the underlying data distribution; the evidence from these results supports a regularization explanation for the effect of pre-training.}
 }
 
@@ -2298,6 +2414,29 @@
 pharmaceutiques dans leur d{\'{e}}couverte de nouveaux m{\'{e}}dicaments.}
 }
 
+@TECHREPORT{Erhan-vis-techreport-2010,
+       author = {Erhan, Dumitru and Courville, Aaron and Bengio, Yoshua},
+        title = {Understanding Representations Learned in Deep Architectures},
+       number = {1355},
+         year = {2010},
+  institution = {Universit{\'{e}} de Montr{\'{e}}al/DIRO},
+     abstract = {Deep architectures have demonstrated state-of-the-art performance in a variety of
+settings, especially with vision datasets. Deep learning algorithms are based on learning
+several levels of representation of the input. Beyond test-set performance, there
+is a need for qualitative comparisons of the solutions learned by various deep architectures,
+focused on those learned representations. One of the goals of our research
+is to improve tools for finding good qualitative interpretations of high level features
+learned by such models. We also seek to gain insight into the invariances learned by
+deep networks. To this end, we contrast and compare several techniques for finding
+such interpretations. We applied our techniques on Stacked Denoising Auto-Encoders
+and Deep Belief Networks, trained on several vision datasets. We show that consistent
+filter-like interpretation is possible and simple to accomplish at the unit level. The tools
+developed make it possible to analyze deep models in more depth and accomplish the
+tracing of invariance manifolds for each of the hidden units. We hope that such techniques
+will allow researchers in deep architectures to understand more of how and why
+deep architectures work.}
+}
+
 @INPROCEEDINGS{Erhan2009,
     author = {Erhan, Dumitru and Manzagol, Pierre-Antoine and Bengio, Yoshua and Bengio, Samy and Vincent, Pascal},
   keywords = {Deep Networks},
@@ -2754,6 +2893,11 @@
            url = {http://snowbird.djvuzone.org/2007/abstracts/161.pdf}
 }
 
+@ARTICLE{JMLR-short,
+   journal = {JMLR},
+      year = {-1}
+}
+
 
 @INPROCEEDINGS{Kegl+Bertin+Eck-2008,
      author = {K{\'{e}}gl, Bal{\'{a}}zs and Bertin-Mahieux, Thierry and Eck, Douglas},
@@ -2833,8 +2977,10 @@
     author = {Larochelle, Hugo and Bengio, Yoshua and Turian, Joseph},
      title = {Tractable Multivariate Binary Density Estimation and the Restricted {Boltzmann} Forest},
    journal = {Neural Computation},
+    volume = {22},
+    number = {9},
       year = {2010},
-      note = {To appear}
+     pages = {2285--2307}
 }
 
 @INPROCEEDINGS{Larochelle+Bengio-2008,
@@ -2865,7 +3011,7 @@
     volume = {10},
       year = {2009},
      pages = {1--40},
-  journal = {Journal of Machine Learning Research},
+  crossref = {JMLR-shorter},
   abstract = {Deep multi-layer neural networks have many levels of non-linearities allowing them to compactly represent highly non-linear and highly-varying functions. However, until recently it was not clear how to train such deep networks, since gradient-based optimization starting from random initialization often appears to get stuck in poor solutions. Hinton et al. recently proposed a greedy layer-wise unsupervised learning procedure relying on the training algorithm of restricted {Boltzmann} machines (RBM) to initialize the parameters of a deep belief network (DBN), a generative model with many layers of hidden causal variables. This was followed by the proposal of another greedy layer-wise procedure, relying on the usage of autoassociator networks. In the context of the above optimization problem, we study these algorithms empirically to better understand their success. Our experiments confirm the hypothesis that the greedy layer-wise unsupervised training strategy helps the optimization by initializing weights in a region near a good local minimum, but also implicitly acts as a sort of regularization that brings better generalization and encourages internal distributed representations that are high-level abstractions of the input. We also present a series of experiments aimed at evaluating the link between the performance of deep neural networks and practical aspects of their topology, for example, demonstrating cases where the addition of more depth helps. Finally, we empirically explore simple variants of these training algorithms, such as the use of different RBM input unit distributions, a simple way of combining gradient estimators to improve performance, as well as on-line versions of those algorithms.}
 }
 
@@ -3029,8 +3175,12 @@
     author = {Le Roux, Nicolas and Bengio, Yoshua},
      title = {Deep Belief Networks are Compact Universal Approximators},
    journal = {Neural Computation},
+    volume = {22},
+    number = {8},
       year = {2010},
-      note = {To appear}
+     pages = {2192-2207},
+      issn = {0899-7667},
+  abstract = {Deep Belief Networks (DBN) are generative models with many layers of hidden causal variables, recently introduced by Hinton et al. (2006), along with a greedy layer-wise unsupervised learning algorithm. Building on Le Roux and Bengio (2008) and Sutskever and Hinton (2008), we show that deep but narrow generative networks do not require more parameters than shallow ones to achieve universal approximation. Exploiting the proof technique, we prove that deep but narrow feed-forward neural networks with sigmoidal units can represent any Boolean expression.}
 }
 
 @TECHREPORT{LeRoux-Bengio-2007-TR,
@@ -3986,7 +4136,7 @@
      title = {The Need for Open Source Software in Machine Learning.},
       year = {2007},
       note = {institution: Fraunhofer Publica [http://publica.fraunhofer.de/oai.har] (Germany)},
-  journal = {Journal of Machine Learning Research},
+  crossref = {JMLR-shorter},
   abstract = {all authors: Sonnenburg, S. and Braun, M.L. and Ong, C.S. and Bengio, S. and Bottou, L. and Holmes, G. and {LeCun}, Y. and M{\~{A}}¼ller, K.-R. and Pereira, F. and Rasmussen, C.E. and R{\~{A}}¤tsch, G. and Sch{\~{A}}{\P}lkopf, B. and Smola, A. and Vincent, P. and Weston, J. and Williamson, R.C.
 
 Open source tools have recently reached a level of maturity which makes them suitable for building large-scale real-world systems. At the same time, the field of machine learning has developed a large body of powerful learning algorithms for diverse applications. However, the true potential of these methods is not used, since existing implementations are not openly shared, resulting in software with low usability, and weak interoperability. We argue that this situation can be significantly improved by increasing incentives for researchers to publish their software under an open source model. Additionally, we outline the problems authors are faced with when trying to publish algorithmic implementations of machine learning methods. We believe that a resource of peer reviewed software accompanied by short articles would be highly valuable to both the machine learning and the general scientific community.}
@@ -4004,6 +4154,16 @@
 topics={Mining},cat={J},
 }
 
+@PHDTHESIS{ThesisChapados2010,
+    author = {Chapados, Nicolas},
+     title = {Sequential Machine learning Approaches for Portfolio Management},
+      year = {2010},
+    school = {Universit{\'{e}} de Montr{\'{e}}al},
+  abstract = {[English follow]
+Cette th{\`{e}}se envisage un ensemble de m{\'{e}}thodes permettant aux algorithmes d'apprentissage statistique de mieux traiter la nature s{\'{e}}quentielle des probl{\`{e}}mes de gestion de portefeuilles financiers. Nous d{\'{e}}butons par une consid{\'{e}}ration du probl{\`{e}}me g{\'{e}}n{\'{e}}ral de la composition d'algorithmes d'apprentissage devant g{\'{e}}rer des t{\^{a}}ches s{\'{e}}quentielles, en particulier celui de la mise-{\`{a}}-jour efficace des ensembles d'apprentissage dans un cadre de validation s{\'{e}}quentielle. Nous {\'{e}}num{\'{e}}rons les desiderata que des primitives de composition doivent satisfaire, et faisons ressortir la difficult{\'{e}} de les atteindre de fa{\c c}on rigoureuse et efficace. Nous poursuivons en pr{\'{e}}sentant un ensemble d'algorithmes qui atteignent ces objectifs et pr{\'{e}}sentons une {\'{e}}tude de cas d'un syst{\`{e}}me complexe de prise de d{\'{e}}cision financi{\`{e}}re utilisant ces techniques. Nous d{\'{e}}crivons ensuite une m{\'{e}}thode g{\'{e}}n{\'{e}}rale permettant de transformer un probl{\`{e}}me de d{\'{e}}cision s{\'{e}}quentielle non-Markovien en un probl{\`{e}}me d'apprentissage supervis{\'{e}} en employant un algorithme de recherche bas{\'{e}} sur les K meilleurs chemins. Nous traitons d'une application en gestion de portefeuille o{\`{u}} nous entra{\^{\i}}nons un algorithme d'apprentissage {\`{a}} optimiser directement un ratio de Sharpe (ou autre crit{\`{e}}re non-additif incorporant une aversion au risque). Nous illustrons l'approche par une {\'{e}}tude exp{\'{e}}rimentale approfondie, proposant une architecture de r{\'{e}}seaux de neurones sp{\'{e}}cialis{\'{e}}e {\`{a}} la gestion de portefeuille et la comparant {\`{a}} plusieurs alternatives. Finalement, nous introduisons une repr{\'{e}}sentation fonctionnelle de s{\'{e}}ries chronologiques permettant {\`{a}} des pr{\'{e}}visions d'{\^{e}}tre effectu{\'{e}}es sur un horizon variable, tout en utilisant un ensemble informationnel r{\'{e}}v{\'{e}}l{\'{e}} de mani{\`{e}}re progressive. L'approche est bas{\'{e}}e sur l'utilisation des processus Gaussiens, lesquels fournissent une matrice de covariance compl{\`{e}}te entre tous les points pour lesquels une pr{\'{e}}vision est demand{\'{e}}e. Cette information est utilis{\'{e}}e {\`{a}} bon escient par un algorithme qui transige activement des {\'{e}}carts de cours (price spreads) entre des contrats {\`{a}} terme sur commodit{\'{e}}s. L'approche propos{\'{e}}e produit, hors {\'{e}}chantillon, un rendement ajust{\'{e}} pour le risque significatif, apr{\`{e}}s frais de transactions, sur un portefeuille de 30 actifs.
+This thesis considers a number of approaches to make machine learning algorithms better suited to the sequential nature of financial portfolio management tasks. We start by considering the problem of the general composition of learning algorithms that must handle temporal learning tasks, in particular that of creating and efficiently updating the training sets in a sequential simulation framework. We enumerate the desiderata that composition primitives should satisfy, and underscore the difficulty of rigorously and efficiently reaching them. We follow by introducing a set of algorithms that accomplish the desired objectives, presenting a case-study of a real-world complex learning system for financial decision-making that uses those techniques. We then describe a general method to transform a non-Markovian sequential decision problem into a supervised learning problem using a K-best paths search algorithm. We consider an application in financial portfolio management where we train a learning algorithm to directly optimize a Sharpe Ratio (or other risk-averse non-additive) utility function. We illustrate the approach by demonstrating extensive experimental results using a neural network architecture specialized for portfolio management and compare against well-known alternatives. Finally, we introduce a functional representation of time series which allows forecasts to be performed over an unspecified horizon with progressively-revealed information sets. By virtue of using Gaussian processes, a complete covariance matrix between forecasts at several time-steps is available. This information is put to use in an application to actively trade price spreads between commodity futures contracts. The approach delivers impressive out-of-sample risk-adjusted returns after transaction costs on a portfolio of 30 spreads.}
+}
+
 @ARTICLE{Thierry+al-2008,
     author = {Bertin-Mahieux, Thierry and Eck, Douglas and Maillet, Fran{\c c}ois and Lamere, Paul},
      title = {Autotagger: A Model For Predicting Social Tags from Acoustic Features on Large Music Databases},
@@ -4324,6 +4484,9 @@
       title = {Quadratic Features and Deep Architectures for Chunking},
   booktitle = {North American Chapter of the Association for Computational Linguistics - Human Language Technologies (NAACL HLT)},
        year = {2009},
+      pages = {245--248},
+  publisher = {Association for Computational Linguistics},
+        url = {http://www.aclweb.org/anthology/N/N09/N09-2062},
    abstract = {We experiment with several chunking models. Deeper architectures achieve better generalization. Quadratic filters, a simplification of theoretical model of V1 complex cells, reliably increase accuracy. In fact, logistic regression with quadratic filters outperforms a standard single hidden layer neural network. Adding quadratic filters to logistic regression is almost as effective as feature engineering. Despite predicting each output label independently, our model is competitive with ones that use previous decisions.}
 }
 
@@ -4339,8 +4502,10 @@
 @INPROCEEDINGS{Turian+Ratinov+Bengio-2010,
      author = {Turian, Joseph and Ratinov, Lev and Bengio, Yoshua},
       title = {Word representations: A simple and general method for semi-supervised learning},
-  booktitle = {Association for Computational Linguistics(ACL2010)},
-       year = {2010}
+  booktitle = {Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics(ACL2010)},
+       year = {2010},
+      pages = {384--394},
+  publisher = {Association for Computational Linguistics},
 }
 
 @INPROCEEDINGS{Vincent-Bengio-2003,
@@ -4353,6 +4518,14 @@
 topics={HighDimensional,Kernel,Unsupervised},cat={C},
 }
 
+@ARTICLE{Vincent-JMLR-2010,
+    author = {Vincent, Pascal and Larochelle, Hugo and Lajoie, Isabelle and Bengio, Yoshua and Manzagol, Pierre-Antoine},
+     title = {Stacked Denoising Autoencoders: learning useful representations in a deep network with a local denoising criterion},
+   journal = {JMLR},
+      year = {2010},
+      note = {to appear}
+}
+
 @TECHREPORT{Vincent-TR1316,
        author = {Vincent, Pascal and Larochelle, Hugo and Bengio, Yoshua and Manzagol, Pierre-Antoine},
         title = {Extracting and Composing Robust Features with Denoising Autoencoders},
@@ -4461,6 +4634,11 @@
   publisher = {MIT Press}
 }
 
+@ARTICLE{JMLR,
+   journal = {Journal of Machine Learning Research},
+      year = {-1}
+}
+
 @INPROCEEDINGS{NIPS19,
      editor = {{Sch{\"{o}}lkopf}, Bernhard and Platt, John and Hoffman, Thomas},
       title = {Advances in Neural Information Processing Systems 19 (NIPS'06)},
@@ -4552,19 +4730,19 @@
        year = {-1}
 }
 
-@INPROCEEDINGS{ICML08,
+@PROCEEDINGS{ICML08,
      editor = {Cohen, William W. and McCallum, Andrew and Roweis, Sam T.},
       title = {Proceedings of the Twenty-fifth International Conference on Machine Learning (ICML'08)},
   booktitle = {Proceedings of the Twenty-fifth International Conference on Machine Learning (ICML'08)},
-       year = {-1},
+       year = {2008},
   publisher = {ACM}
 }
 
-@INPROCEEDINGS{ICML07,
+@PROCEEDINGS{ICML07,
      editor = {Ghahramani, Zoubin},
       title = {Proceedings of the 24th International Conference on Machine Learning (ICML'07)},
   booktitle = {Proceedings of the 24th International Conference on Machine Learning (ICML'07)},
-       year = {-1},
+       year = {2007},
   publisher = {ACM}
 }
 
@@ -4692,6 +4870,10 @@
        year = {-1},
   publisher = {Morgan Kaufmann}
 }
+@ARTICLE{JMLR-shorter,
+   journal = {JMLR},
+      year = {-1}
+}
 @INPROCEEDINGS{NIPS1-shorter,
       title = {NIPS'88},
   booktitle = {NIPS 1},
@@ -4826,5 +5008,3 @@
   booktitle = {AISTATS'2009},
        year = {-1}
 }
-
-