#### Filter Results:

#### Publication Year

1989

2016

#### Publication Type

#### Co-author

#### Publication Venue

#### Data Set Used

#### Key Phrases

Learn More

(inc. logic of biosystems, cybernetics and bionics). Abstract We consider a Perceptron with N i input units, one output and a yet unspecified number of hidden units. This Perceptron must be able to learn a given but arbitrary set of input-output examples. By sequential learning we mean that groups of patterns, pertaining to the same class, are sequentially… (More)

- Yaroslav Ganin, Evgeniya Ustinova, Hana Ajakan, Pascal Germain, Hugo Larochelle, François Laviolette +2 others
- ArXiv
- 2015

We introduce a new representation learning approach for domain adaptation, in which data at training and test time come from similar but different distributions. Our approach is directly inspired by the theory on domain adaptation suggesting that, for effective domain transfer to be achieved, predictions must be made based on features that cannot… (More)

We propose new PAC-Bayes bounds for the risk of the weighted majority vote that depend on the mean and variance of the error of its associated Gibbs classifier. We show that these bounds can be smaller than the risk of the Gibbs classifier and can be arbitrarily close to zero even if the risk of the Gibbs classifier is close to 1/2. Moreover, we show that… (More)

In this paper, we We a close look at the problem of l&ing simple neural concepts under the uniform diseibution of examples By simple neural concepts we mean concepts that can be represented as simple combinations of perceptrons (halfspaces). One such class of concepts is the class of halfspace intersections. By formalizing the problem of learning halfspace… (More)

We extend the classical algorithms of Valiant and Haussler for learning compact conjunctions and disjunctions of Boolean attributes to allow features that are constructed from the data and to allow a trade-off between accuracy and complexity. The result is a general-purpose learning machine, suitable for practical learning tasks, that we call the set… (More)

We present a general PAC-Bayes theorem from which all known PAC-Bayes risk bounds are obtained as particular cases. We also propose different learning algorithms for finding linear classifiers that minimize these bounds. These learning algorithms are generally competitive with both AdaBoost and the SVM.

We propose to construct a weighted majority vote on a set of basis functions by minimizing a risk bound (called the C-bound) that depends on the first two moments of the margin of the Q-convex combination realized on the data. This bound minimization algorithm turns out to be a quadratic program that can be efficiently solved. A first version of the… (More)

We show that convex KL-regularized objective functions are obtained from a PAC-Bayes risk bound when using convex loss functions for the stochastic Gibbs classifier that upper-bound the standard zero-one loss used for the weighted majority vote. By restricting ourselves to a class of posteriors, that we call quasi uniform, we propose a simple coordinate… (More)

We investigate, within the PAC learning model, the problem of learning nonoverlapping perceptron networks (also known as read-once formulas over a weighted threshold basis). These are loop-free neural nets in which each node has only one outgoing weight. We give a polynomial time algorithm that PAC learns any nonoverlapping perceptron network using examples… (More)

We generalize the classical algorithms of Valiant and Haussler for learning conjunctions and disjunctions of Boolean attributes to the problem of learning these functions over arbitrary sets of features; including features that are constructed from the data. The result is a general-purpose learning machine , suitable for practical learning tasks, that we… (More)