Q-learning with neural network function approximation (neural Q-learning for short) is among the most prevalent deep reinforcement learning algorithms. Despite its empirical success, the non-asymptotic convergence rate of neural Q-learning remains virtually unknown. In this paper, we present a finite-time analysis of a neural Q-learning algorithm, where the data are generated from a Markov decision process and the action-value function is approximated by a deep ReLU neural network. We prove that neural Q-learning finds the optimal policy with $O(1/\sqrt{T})$ convergence rate if the neural function approximator is sufficiently overparameterized, where $T$ is the number of iterations. To our best knowledge, our result is the first finite-time analysis of neural Q-learning under non-i.i.d. data assumption.

In most fuzzy control applications (applying classical fuzzy reasoning), the reasoning method requires a complete fuzzy rule-base, i.e all the possible observations must be covered by the antecedents of the fuzzy rules, which is not always available. Fuzzy control systems based on the Fuzzy Rule Interpolation (FRI) concept play a major role in different platforms, in case if only a sparse fuzzy rule-base is available. This cases the fuzzy model contains only the most relevant rules, without covering all the antecedent universes. The first FRI toolbox being able to handle different FRI methods was developed by Johanyak et. al. in 2006 for the MATLAB environment. The goal of this paper is to introduce some details of the adaptation of the FRI toolbox to support the GNU/OCTAVE programming language. The OCTAVE Fuzzy Rule Interpolation (OCTFRI) Toolbox is an open-source toolbox for OCTAVE programming language, providing a large functionally compatible subset of the MATLAB FRI toolbox as well as many extensions. The OCTFRI Toolbox includes functions that enable the user to evaluate Fuzzy Inference Systems (FISs) from the command line and from OCTAVE scripts, read/write FISs and OBS to/from files, and produce a graphical visualisation of both the membership functions and the FIS outputs. Future work will focus on implementing advanced fuzzy inference techniques and GUI tools.

Maximizing the (log) likelihood is equivalent to minimizing the binary cross entropy. There is literally no difference between the two objective functions, so there can be no difference between the resulting model or its characteristics. This of course, can be extended quite simply to the multiclass case using softmax cross-entropy and the so-called multinoulli likelihood, so there is no difference when doing this for multiclass cases as is typical in, say, neural networks. The difference between MLE and cross-entropy is that MLE represents a structured and principled approach to modeling and training, and binary/softmax cross-entropy simply represent special cases of that applied to problems that people typically care about. After that aside on maximum likelihood estimation, let's delve more into the relationship between negative log likelihood and cross entropy.

We design a new provably efficient algorithm for episodic reinforcement learning with generalized linear function approximation. We analyze the algorithm under a new expressivity assumption that we call "optimistic closure," which is strictly weaker than assumptions from prior analyses for the linear setting. With optimistic closure, we prove that our algorithm enjoys a regret bound of $\tilde{O}(\sqrt{d^3 T})$ where $d$ is the dimensionality of the state-action features and $T$ is the number of episodes. This is the first statistically and computationally efficient algorithm for reinforcement learning with generalized linear functions.

High-dimensional prediction is a challenging problem setting for traditional statistical models. Although regularization improves model performance in high dimensions, it does not sufficiently leverage knowledge on feature importances held by domain experts. As an alternative to standard regularization techniques, we propose Distance Metric Learning Regularization (DMLreg), an approach for eliciting prior knowledge from domain experts and integrating that knowledge into a regularized linear model. First, we learn a Mahalanobis distance metric between observations from pairwise similarity comparisons provided by an expert. Then, we use the learned distance metric to place prior distributions on coefficients in a linear model. Through experimental results on a simulated high-dimensional prediction problem, we show that DMLreg leads to improvements in model performance when the domain expert is knowledgeable.

What AI tools are needed for SE? Ideally, we should have simple rules that peek at data, then say "use this tool" or "use that tool". To find such a rule, we explored 120 different data sets addressing numerous problems, including bad smell detection, predicting Github issue close time, bug report analysis, defect prediction and dozens of other non-SE problems. To this data, we apply a SE-based tool that (a)~out-performs the state-of-the-art for these SE problems yet (b)~fails very badly on standard AI problems. In those results, we can find a simple rule for when to use/avoid the SE-based tool. SE data is often about infrequent issues, like the occasional defect, or the rarely exploited security violation, or the requirement that holds for one special case. But as we show, standard AI tools work best when the target is relatively more frequent. Also, we can exploit these special properties of SE, to great effect (to rapidly find better optimizations for SE tasks via a tactic called "dodging", explained in this paper). More generally, this result says we need a new kind of SE research for developing new AI tools that are more suited to SE problems.

Continual Learning is a learning paradigm where machine learning mode ls are trained with sequential or streaming tasks. Two notable directions among the recent adva nces in continual learning with neural networks are ( i) variational Bayes based regularization by learning priors from pre vious tasks, and, ( ii) learning the structure of deep networks to adapt to new tasks. S o far, these two approaches have been orthogonal. We present a principled nonparametric Bayesian appr oach for learning the structure of feed-forward neural networks, addressing the shortcomings o f both these approaches. In our model, the number of nodes in each hidden layer can automatically grow with the in troduction of each new task, and inter-task transfer occurs through the overlapping of differ ent sparse subsets of weights learned by different tasks. On benchmark datasets, our model performs comparably or better than the state-of-the-art approaches, while also being able to adaptively infer the evolving network structure in the continual learning setting.

In this paper, we improve the PAC-Bayesian error bound for linear regression derived in Germain et al. [10]. The improvements are twofold. First, the proposed error bound is tighter, and converges to the generalization loss with a well-chosen temperature parameter. Second, the error bound also holds for training data that are not independently sampled. In particular, the error bound applies to certain time series generated by well-known classes of dynamical models, such as ARX models.

Bayesian learning of model parameters in neural networks is important in scenarios where estimates with well-calibrated uncertainty are important. In this paper, we propose Bayesian quantized networks (BQNs), quantized neural networks (QNNs) for which we learn a posterior distribution over their discrete parameters. We provide a set of efficient algorithms for learning and prediction in BQNs without the need to sample from their parameters or activations, which not only allows for differentiable learning in QNNs, but also reduces the variance in gradients. We demonstrate BQNs achieve both lower predictive errors and better-calibrated uncertainties than E-QNN (with less than 20% of the negative log-likelihood). A Bayesian approach to deep learning considers the network's parameters to be random variables and seeks to infer their posterior distribution given the training data. Models trained this way, called Bayesian neural networks (BNNs) (Wang & Y eung, 2016), in principle have well-calibrated uncertainties when they make predictions, which is important in scenarios such as active learning and reinforcement learning (Gal, 2016). Furthermore, the posterior distribution over the model parameters provides valuable information for evaluation and compression of neural networks. There are three main challenges in using BNNs: (1) Intractable posterior: Computing and storing the exact posterior distribution over the network weights is intractable due to the complexity and high-dimensionality of deep networks. These challenges are typically addressed either by making simplifying assumptions about the distributions of the parameters and activations, or by using sampling-based approaches, which are expensive and unreliable (likely to overestimate the uncertainties in predictions). Our goal is to propose a sampling-free method which uses probabilistic propagation to deterministically learn BNNs. A seemingly unrelated area of deep learning research is that of quantized neural networks (QNNs), which offer advantages of computational and memory efficiency compared to continuous-valued models.

Despite the availability of qualified research personnel, up-to-date research facilities and experience in developing applied research and innovation, many worldwide research institutions face difficulties when managing contracted Research and Development (R&D) projects due to expectations from Industry (private sector). Such difficulties have motivated funding agents to create evaluation processes to check whether the operational procedures of funded research institutions are sufficient to provide timely answers to demand for innovation from industry and also to identify aspects that require quality improvement in research development. For this purpose, several multiple criteria decision-making approaches can be applied. Among the available multiple criteria approaches, sorting methods are one prominent tool to evaluate the operational capacity. However, the first difficulty in applying multiple criteria sorting methods is the need to hierarchically structure multiple criteria in order to represent the intended decision process. Additional challenges include the elicitation of the preference information and the definition of criteria evaluation, since these are frequently affected by some imprecision. In this paper, a new sorting method is proposed to deal with all of those critical points simultaneously. To consider multiple levels for the decision criteria, the FlowSort method is extended to account for hierarchical criteria. To deal with imprecise data, the FlowSort is integrated with fuzzy approaches. To yield solutions that consider fluctuations from imprecise weights, the Stochastic Multicriteria Acceptability Analysis is used. Finally, the proposed method is applied to the evaluation of research institutions, classifying them according to their operational maturity for development of applied research.