Abstract:
We propose a theory that relates difficulty of learning in deep architectures to culture and language. It is articulated around the following hypotheses: (1) learning in an individual human brain is hampered by the presence of effective local minima; (2) this optimization difficulty is particularly important when it comes to learning higher-level abstractions, i.e., concepts that cover a vast and highly-nonlinear span of sensory configurations; (3) such high-level abstractions are best represented in brains by the composition of many levels of representation, i.e., by deep architectures; (4) a human brain can learn such high-level abstractions if guided by the signals produced by other humans, which act as hints or indirect supervision for these high-level abstractions; and (5), language and the recombination and optimization of mental concepts provide an efficient evolutionary recombination operator, and this gives rise to rapid search in the space of communicable ideas that help humans build up better high-level internal representations of their world. These hypotheses put together imply that human culture and the evolution of ideas have been crucial to counter an optimization difficulty: this optimization difficulty would otherwise make it very difficult for human brains to capture high-level knowledge of the world. The theory is grounded in experimental observations of the difficulties of training deep artificial neural networks. Plausible consequences of this theory for the efficiency of cultural evolutions are sketched.

Abstract:
Learning algorithms related to artificial neural networks and in particular for Deep Learning may seem to involve many bells and whistles, called hyper-parameters. This chapter is meant as a practical guide with recommendations for some of the most commonly used hyper-parameters, in particular in the context of learning algorithms based on back-propagated gradient and gradient-based optimization. It also discusses how to deal with the fact that more interesting results can be obtained when allowing one to adjust many hyper-parameters. Overall, it describes elements of the practice used to successfully and efficiently train and debug large-scale and often deep multi-layer neural networks. It closes with open questions about the training difficulties observed with deeper architectures.

Abstract:
Deep learning research aims at discovering learning algorithms that discover multiple levels of distributed representations, with higher levels representing more abstract concepts. Although the study of deep learning has already led to impressive theoretical results, learning algorithms and breakthrough experiments, several challenges lie ahead. This paper proposes to examine some of these challenges, centering on the questions of scaling deep learning algorithms to much larger models and datasets, reducing optimization difficulties due to ill-conditioning or local minima, designing more efficient and powerful inference and sampling procedures, and learning to disentangle the factors of variation underlying the observed data. It also proposes a few forward-looking research directions aimed at overcoming these challenges.

Abstract:
Stochastic neurons can be useful for a number of reasons in deep learning models, but in many cases they pose a challenging problem: how to estimate the gradient of a loss function with respect to the input of such stochastic neurons, i.e., can we "back-propagate" through these stochastic neurons? We examine this question, existing approaches, and present two novel families of solutions, applicable in different settings. In particular, it is demonstrated that a simple biologically plausible formula gives rise to an an unbiased (but noisy) estimator of the gradient with respect to a binary stochastic neuron firing probability. Unlike other estimators which view the noise as a small perturbation in order to estimate gradients by finite differences, this estimator is unbiased even without assuming that the stochastic perturbation is small. This estimator is also interesting because it can be applied in very general settings which do not allow gradient back-propagation, including the estimation of the gradient with respect to future rewards, as required in reinforcement learning setups. We also propose an approach to approximating this unbiased but high-variance estimator by learning to predict it using a biased estimator. The second approach we propose assumes that an estimator of the gradient can be back-propagated and it provides an unbiased estimator of the gradient, but can only work with non-linearities unlike the hard threshold, but like the rectifier, that are not flat for all of their range. This is similar to traditional sigmoidal units but has the advantage that for many inputs, a hard decision (e.g., a 0 output) can be produced, which would be convenient for conditional computation and achieving sparse representations and sparse gradients.

Abstract:
We show that Langevin MCMC inference in an energy-based model with latent variables has the property that the early steps of inference, starting from a stationary point, correspond to propagating error gradients into internal layers, similarly to back-propagation. The error that is back-propagated is with respect to visible units that have received an outside driving force pushing them away from the stationary point. Back-propagated error gradients correspond to temporal derivatives of the activation of hidden units. This observation could be an element of a theory for explaining how brains perform credit assignment in deep hierarchies as efficiently as back-propagation does. In this theory, the continuous-valued latent variables correspond to averaged voltage potential (across time, spikes, and possibly neurons in the same minicolumn), and neural computation corresponds to approximate inference and error back-propagation at the same time.

Abstract:
We propose to exploit {\em reconstruction} as a layer-local training signal for deep learning. Reconstructions can be propagated in a form of target propagation playing a role similar to back-propagation but helping to reduce the reliance on derivatives in order to perform credit assignment across many levels of possibly strong non-linearities (which is difficult for back-propagation). A regularized auto-encoder tends produce a reconstruction that is a more likely version of its input, i.e., a small move in the direction of higher likelihood. By generalizing gradients, target propagation may also allow to train deep networks with discrete hidden units. If the auto-encoder takes both a representation of input and target (or of any side information) in input, then its reconstruction of input representation provides a target towards a representation that is more likely, conditioned on all the side information. A deep auto-encoder decoding path generalizes gradient propagation in a learned way that can could thus handle not just infinitesimal changes but larger, discrete changes, hopefully allowing credit assignment through a long chain of non-linear operations. In addition to each layer being a good auto-encoder, the encoder also learns to please the upper layers by transforming the data into a space where it is easier to model by them, flattening manifolds and disentangling factors. The motivations and theoretical justifications for this approach are laid down in this paper, along with conjectures that will have to be verified either mathematically or experimentally, including a hypothesis stating that such auto-encoder mediated target propagation could play in brains the role of credit assignment through many non-linear, noisy and discrete transformations.

Abstract:
We describe a general method to transform a non-Markovian sequential decision problem into a supervised learning problem using a K-best-paths algorithm. We consider an application in financial portfolio management where we can train a controller to directly optimize a Sharpe Ratio (or other risk-averse non-additive) utility function. We illustrate the approach by demonstrating experimental results using a kernel-based controller architecture that would not normally be considered in traditional reinforcement learning or approximate dynamic programming. We further show that using a non-additive criterion (incremental Sharpe Ratio) yields a noisy K-best-paths extraction problem, that can give substantially improved performance.

Abstract:
For discrete data, the likelihood $P(x)$ can be rewritten exactly and parametrized into $P(X = x) = P(X = x | H = f(x)) P(H = f(x))$ if $P(X | H)$ has enough capacity to put no probability mass on any $x'$ for which $f(x')\neq f(x)$, where $f(\cdot)$ is a deterministic discrete function. The log of the first factor gives rise to the log-likelihood reconstruction error of an autoencoder with $f(\cdot)$ as the encoder and $P(X|H)$ as the (probabilistic) decoder. The log of the second term can be seen as a regularizer on the encoded activations $h=f(x)$, e.g., as in sparse autoencoders. Both encoder and decoder can be represented by a deep neural network and trained to maximize the average of the optimal log-likelihood $\log p(x)$. The objective is to learn an encoder $f(\cdot)$ that maps $X$ to $f(X)$ that has a much simpler distribution than $X$ itself, estimated by $P(H)$. This "flattens the manifold" or concentrates probability mass in a smaller number of (relevant) dimensions over which the distribution factorizes. Generating samples from the model is straightforward using ancestral sampling. One challenge is that regular back-propagation cannot be used to obtain the gradient on the parameters of the encoder, but we find that using the straight-through estimator works well here. We also find that although optimizing a single level of such architecture may be difficult, much better results can be obtained by pre-training and stacking them, gradually transforming the data distribution into one that is more easily captured by a simple parametric model.

Abstract:
We evaluate natural gradient, an algorithm originally proposed in Amari (1997), for learning deep models. The contributions of this paper are as follows. We show the connection between natural gradient and three other recently proposed methods for training deep models: Hessian-Free (Martens, 2010), Krylov Subspace Descent (Vinyals and Povey, 2012) and TONGA (Le Roux et al., 2008). We describe how one can use unlabeled data to improve the generalization error obtained by natural gradient and empirically evaluate the robustness of the algorithm to the ordering of the training set compared to stochastic gradient descent. Finally we extend natural gradient to incorporate second order information alongside the manifold information and provide a benchmark of the new algorithm using a truncated Newton approach for inverting the metric matrix instead of using a diagonal approximation of it.

Abstract:
What do auto-encoders learn about the underlying data generating distribution? Recent work suggests that some auto-encoder variants do a good job of capturing the local manifold structure of data. This paper clarifies some of these previous observations by showing that minimizing a particular form of regularized reconstruction error yields a reconstruction function that locally characterizes the shape of the data generating density. We show that the auto-encoder captures the score (derivative of the log-density with respect to the input). It contradicts previous interpretations of reconstruction error as an energy function. Unlike previous results, the theorems provided here are completely generic and do not depend on the parametrization of the auto-encoder: they show what the auto-encoder would tend to if given enough capacity and examples. These results are for a contractive training criterion we show to be similar to the denoising auto-encoder training criterion with small corruption noise, but with contraction applied on the whole reconstruction function rather than just encoder. Similarly to score matching, one can consider the proposed training criterion as a convenient alternative to maximum likelihood because it does not involve a partition function. Finally, we show how an approximate Metropolis-Hastings MCMC can be setup to recover samples from the estimated distribution, and this is confirmed in sampling experiments.