In recent work, it was shown that combining multi-kernel based support vector machines (SVMs) can lead to near state-of-the-art performance on an action recognition dataset (HMDB-51 dataset). This was 0.4\% lower than frameworks that used hand-crafted features in addition to the deep convolutional feature extractors. In the present work, we show that combining distributed Gaussian Processes with multi-stream deep convolutional neural networks (CNN) alleviate the need to augment a neural network with hand-crafted features. In contrast to prior work, we treat each deep neural convolutional network as an expert wherein the individual predictions (and their respective uncertainties) are combined into a Product of Experts (PoE) framework.

A general framework for multi-label classification(MLC) called multi-label error-correcting code (ML-ECC) utilizes coding schemes in communication to improve MLC performance. The framework includes some key algorithms for some special cases of MLC, such as binary relevance and random k-labelsets. Nevertheless, current ML-ECC algorithms are usually designed for one or a few evaluation criteria, and thus may suffer from bad performance with respect to other criteria. In this paper, we propose a ML-ECC algorithm that takes the evaluation criteria into account within the error-correcting code.This algorithm, named cost-sensitive reference pair encoding(CSRPE), first transforms the MLC problem into exponentially many binary classification problems based on the criterion information and a series of reduction steps from MLC to multi-class classification and then to binary classification. The exponentially many binary classifiers cause training and prediction challenges.We resolve the training challenge by random sampling and the prediction challenge by nearest-neighbor decoding. Extensive experimental results show that CSRPE achieves stable convergence, and performs better than other ML-ECC algorithms and the state-of-the-art cost-sensitive MLC algorithms across different criteria. Furthermore, we demonstrate the potential of CSRPE in preserving the criterion information by extending it to a novel multi-label active learning algorithm. The algorithm calculates the uncertainty of each unlabeled example in the coding space of CSRPE and queries the most uncertain one. Experimental results demonstrate that the proposed algorithm is superior to existing multi-label active learning algorithms.

Under Markovian assumptions, we leverage a Central Limit Theorem (CLT) for the empirical measure in the test statistic of the composite hypothesis Hoeffding test so as to establish weak convergence results for the test statistic, and, thereby, derive a new estimator for the threshold needed by the test. We first show the advantages of our estimator over an existing estimator by conducting extensive numerical experiments. We find that our estimator controls better for false alarms while maintaining satisfactory detection probabilities. We then apply the Hoeffding test with our threshold estimator to detecting anomalies in two distinct applications domains: one in communication networks and the other in transportation networks. The former application seeks to enhance cyber security and the latter aims at building smarter transportation systems in cities.

About this course: This course aims to help you to draw better statistical inferences from empirical research. First, we will discuss how to correctly interpret p-values, effect sizes, confidence intervals, Bayes Factors, and likelihood ratios, and how these statistics answer different questions you might be interested in. Then, you will learn how to design experiments where the false positive rate is controlled, and how to decide upon the sample size for your study, for example in order to achieve high statistical power. Subsequently, you will learn how to interpret evidence in the scientific literature given widespread publication bias, for example by learning about p-curve analysis. Finally, we will talk about how to do philosophy of science, theory construction, and cumulative science, including how to perform replication studies, why and how to pre-register your experiment, and how to share your results following Open Science principles. In practical, hands on assignments, you will learn how to simulate t-tests to learn which p-values you can expect, calculate likelihood ratio's and get an introduction the binomial Bayesian statistics, and learn about the positive predictive value which expresses the probability published research findings are true.

This is part of a project I've been working in that involves using ML techniques to robot control. The first one is applying evolutionary algorithms to a neural controller. You cna find a Jupyter Notebook on the linked repository.

This course includes interactive demonstrations which are intended to stimulate interest and to help students gain intuition about how artificial intelligence methods work under a variety of circumstances. This course introduces students to the basic knowledge representation, problem solving, and learning methods of artificial intelligence. Upon completion of 6.034, students should be able to develop intelligent systems by assembling solutions to concrete computational problems; understand the role of knowledge representation, problem solving, and learning in intelligent-system engineering; and appreciate the role of problem solving, vision, and language in understanding human intelligence from a computational perspective.

Python is a very popular high-level language created by Guido van Rossum and first released in 1991. Python is named after the greatest comedy act of all time, Monty Python. Python can be used to create pretty much any type of application. Python has been popular for many years and it's popularity shows no signs of stopping anytime soon. Been an in demand language, knowing Python is definitely something beneficial for your career as a software developer. Python is a very widely used programming languages that can do almost anything. Having working knowledge of high level programming languages is something any software developer should have. Whether it is a script you need to run or a complete application, Python is something you can use in your daily life as a programmer. Here's a list of some of the best Python books, courses, videos and tutorials in 2017 to help you learn Python.

About this course: In this course you will learn a variety of matrix factorization and hybrid machine learning techniques for recommender systems. Starting with basic matrix factorization, you will understand both the intuition and the practical details of building recommender systems based on reducing the dimensionality of the user-product preference space. Then you will learn about techniques that combine the strengths of different algorithms into powerful hybrid recommenders.

About this course: This course provides a rigorous introduction to the R programming language, with a particular focus on using R for software development in a data science setting. Whether you are part of a data science team or working individually within a community of developers, this course will give you the knowledge of R needed to make useful contributions in those settings. As the first course in the Specialization, the course provides the essential foundation of R needed for the following courses. We cover basic R concepts and language fundamentals, key concepts like tidy data and related "tidyverse" tools, processing and manipulation of complex and large datasets, handling textual data, and basic data science tasks. Upon completing this course, learners will have fluency at the R console and will be able to create tidy datasets from a wide range of possible data sources.

Welcome to the Lenet tutorial using TensorFlow. From being a long time user of Theano, migrating to TensorFlow is not that easy. Recently, tensorflow is showing strong performance leading to many defecting from theano to tensorflow. I am one such defector. This repository contains an implementation Lenet, the hello world of deep CNNs and is my first exploratory experimentation with TensorFlow.