This paper applies deep learning to the prediction of Portuguese high school grades. A multilayer perceptron and a multiple linear regression implementation are undertaken. The objective is demonstrate adequacy as quantitative explanatory paradigm when compared with classical econometrics approach. results encompass point predictions, intervals, variable gradients, impact an increase in class s...

By using abundant unlabeled data, semi-supervised learning approaches have been found useful in various tasks. Existing approaches, however, neglect the fact that the storage available for the learning process is different under different situations, and thus, the learning approaches should be flexible subject to the storage budget limit. In this paper, we focus on graph-based semi-supervised l...

We introduce the first temporal-difference learning algorithms that converge with smooth value function approximators, such as neural networks. Conventional temporal-difference (TD) methods, such as TD(λ), Q-learning and Sarsa have been used successfully with function approximation in many applications. However, it is well known that off-policy sampling, as well as nonlinear function approximat...

Consider a given value function on states of a Markov decision problem, as might result from applying a reinforcement learning algorithm. Unless this value function equals the corresponding optimal value function, at some states there will be a discrepancy, which is natural to call the Bellman residual, between what the value function speciies at that state and what is obtained by a one-step lo...

In this theoretical paper we are concerned with the problem of learning a value function by a smooth general function approximator, to solve a deterministic episodic control problem in a large continuous state space. It is shown that learning the gradient of the value-function at every point along a trajectory generated by a greedy policy is a sufficient condition for the trajectory to be local...

In this paper we introduce two novel methods for performing Bayesian network structure search that make use of Gaussian Process regression. Using a relatively small number of samples from the posterior distribution of Bayesian networks, we are able to find an accurate function approximator based on Gaussian Processes. This allows us to remove our dependency on the data during the search and lea...

Value functions can speed the learning of a solution to Markov Decision Problems by providing a prediction of reinforcement against which received reinforcement is compared. Once the learned values relatively reect the optimal ordering of actions, further learning is not necessary. In fact, further learning can lead to the disruption of the optimal policy if the value function is implemented wi...

Reinforcement learning problems are commonly tackled by estimating the optimal value function. In many real-world problems, learning this value function requires a function approximator, which maps states to values via a parameterized function. In practice, the success of function approximators depends on the ability of the human designer to select an appropriate representation for the value fu...

We study solvers of nonogram puzzles, which are good examples of constraint-satisfaction problems. Given an optimal solving module for solving a given line, we compare performance of three algorithmic solvers used to select the order in which to solve lines with a reinforcement-learningbased solver. The reinforcement-learning (RL) solver uses a measure of reduction of distance to goal as a rewa...