Distance Learning


Top 10 Free Deep Learning Massive Open Online Courses

#artificialintelligence

This free course is published by the Massachusetts Institute of Technology (MIT). This is a week-long, self-paced course that will introduce you to Deep Learning technology and many of its industrial applications, from translation algorithms to image and object recognition, game playing, and more.


Accelerated Gradient Methods for Stochastic Optimization and Online Learning

Neural Information Processing Systems

Gradient descent methods, though highly scalable and easy to implement, are known to converge slowly on these problems. In this paper, we develop novel accelerated gradient methods for stochastic optimization while still preserving their computational simplicity and scalability. The proposed algorithm, called SAGE (Stochastic Accelerated GradiEnt), exhibits fast convergence rates on stochastic optimization with both convex and strongly convex objectives. Experimental results show that SAGE is faster than recent (sub)gradient methods including FOLOS, SMIDAS and SCD. Moreover, SAGE can also be extended for online learning, resulting in a simple but powerful algorithm.


The Complete Machine Learning Course with Python

#artificialintelligence

Machine Learning Engineers earn on average $166,000 - become an ideal candidate with this course! Machine Learning Engineers earn on average $166,000 - become an ideal candidate with this course! Comment Policy: Please write your comments according to the topic of this page posting. Comments containing a link will not be displayed before approval.


Confusion-Based Online Learning and a Passive-Aggressive Scheme

Neural Information Processing Systems

This paper provides the first ---to the best of our knowledge--- analysis of online learning algorithms for multiclass problems when the {\em confusion} matrix is taken as a performance measure. The work builds upon recent and elegant results on noncommutative concentration inequalities, i.e. concentration inequalities that apply to matrices, and more precisely to matrix martingales. We do establish generalization bounds for online learning algorithm and show how the theoretical study motivate the proposition of a new confusion-friendly learning procedure. This learning algorithm, called \copa (for COnfusion Passive-Aggressive) is a passive-aggressive learning algorithm; it is shown that the update equations for \copa can be computed analytically, thus allowing the user from having to recours to any optimization package to implement it. Papers published at the Neural Information Processing Systems Conference.


On higher-order perceptron algorithms

Neural Information Processing Systems

A new algorithm for on-line learning linear-threshold functions is proposed which efficiently combines second-order statistics about the data with the logarithmic behavior" of multiplicative/dual-norm algorithms. An initial theoretical analysis is provided suggesting that our algorithm might be viewed as a standard Perceptron algorithm operating on a transformed sequence of examples with improved margin properties. We also report on experiments carried out on datasets from diverse domains, with the goal of comparing to known Perceptron algorithms (first-order, second-order, additive, multiplicative). Our learning procedure seems to generalize quite well, and converges faster than the corresponding multiplicative baseline algorithms." Papers published at the Neural Information Processing Systems Conference.


DUOL: A Double Updating Approach for Online Learning

Neural Information Processing Systems

In most online learning algorithms, the weights assigned to the misclassified examples (or support vectors) remain unchanged during the entire learning process. This is clearly insufficient since when a new misclassified example is added to the pool of support vectors, we generally expect it to affect the weights for the existing support vectors. In this paper, we propose a new online learning method, termed Double Updating Online Learning", or "DUOL" for short. Instead of only assigning a fixed weight to the misclassified example received in current trial, the proposed online learning algorithm also tries to update the weight for one of the existing support vectors. We show that the mistake bound can be significantly improved by the proposed online learning method. Encouraging experimental results show that the proposed technique is in general considerably more effective than the state-of-the-art online learning algorithms."


Learning the Dependency Structure of Latent Factors

Neural Information Processing Systems

In this paper, we study latent factor models with the dependency structure in the latent space. We propose a general learning framework which induces sparsity on the undirected graphical model imposed on the vector of latent factors. A novel latent factor model SLFA is then proposed as a matrix factorization problem with a special regularization term that encourages collaborative reconstruction. The main benefit (novelty) of the model is that we can simultaneously learn the lower-dimensional representation for data and model the pairwise relationships between latent factors explicitly. An on-line learning algorithm is devised to make the model feasible for large-scale learning problems.


Efficient Online Learning via Randomized Rounding

Neural Information Processing Systems

Most online algorithms used in machine learning today are based on variants of mirror descent or follow-the-leader. In this paper, we present an online algorithm based on a completely different approach, which combines random playout'' and randomized rounding of loss subgradients. As an application of our approach, we provide the first computationally efficient online algorithm for collaborative filtering with trace-norm constrained matrices. As a second application, we solve an open question linking batch learning and transductive online learning. Papers published at the Neural Information Processing Systems Conference.


(Nearly) Optimal Algorithms for Private Online Learning in Full-information and Bandit Settings

Neural Information Processing Systems

We provide a general technique for making online learning algorithms differentially private, in both the full information and bandit settings. Our technique applies to algorithms that aim to minimize a \emph{convex} loss function which is a sum of smaller convex loss terms, one for each data point. We modify the popular \emph{mirror descent} approach, or rather a variant called \emph{follow the approximate leader}. The technique leads to the first nonprivate algorithms for private online learning in the bandit setting. In the full information setting, our algorithms improve over the regret bounds of previous work.


Online Learning in Markov Decision Processes with Adversarially Chosen Transition Probability Distributions

Neural Information Processing Systems

We study the problem of online learning Markov Decision Processes (MDPs) when both the transition distributions and loss functions are chosen by an adversary. We present an algorithm that, under a mixing assumption, achieves $O(\sqrt{T\log \Pi } \log \Pi)$ regret with respect to a comparison set of policies $\Pi$. The regret is independent of the size of the state and action spaces. When expectations over sample paths can be computed efficiently and the comparison set $\Pi$ has polynomial size, this algorithm is efficient. We also consider the episodic adversarial online shortest path problem.