The birth of artificial-intelligence research as an autonomous discipline is generally thought to have been the monthlong Dartmouth Summer Research Project on Artificial Intelligence in 1956, which convened 10 leading electrical engineers -- including MIT's Marvin Minsky and Claude Shannon -- to discuss "how to make machines use language" and "form abstractions and concepts." A decade later, impressed by rapid advances in the design of digital computers, Minsky was emboldened to declare that "within a generation ... the problem of creating'artificial intelligence' will substantially be solved." The problem, of course, turned out to be much more difficult than AI's pioneers had imagined. In recent years, by exploiting machine learning -- in which computers learn to perform tasks from sets of training examples -- artificial-intelligence researchers have built special-purpose systems that can do things like interpret spoken language or play Jeopardy with great success. But according to Tomaso Poggio, the Eugene McDermott Professor of Brain Sciences and Human Behavior at MIT, "These recent achievements have, ironically, underscored the limitations of computer science and artificial intelligence. We do not yet understand how the brain gives rise to intelligence, nor do we know how to build machines that are as broadly intelligent as we are."

The C5.0 algorithm uses the Max-Gain method of selecting the best attribute. H measures the information content or entropy in bits (i.e., number of yes/no questions that must be asked) associated with a set S of examples, which consists of the subset P of positive examples and subset N of negative examples. Note: 0 H(P,N) 1, where 0 no information, and 1 maximum information. Half the examples in S are positive and half are negative. Say all of the examples in S are positive and none are negative.

Topics covered include: representation and inference in first-order logic, modern deterministic and decision-theoretic planning techniques, basic supervised learning methods, and Bayesian network inference and learning. This course was also taught as part of the Singapore-MIT Alliance (SMA) programme as course number SMA 5504 (Techniques in Artificial Intelligence).

Time series forecasting can be framed as a supervised learning problem. This re-framing of your time series data allows you access to the suite of standard linear and nonlinear machine learning algorithms on your problem. In this post, you will discover how you can re-frame your time series problem as a supervised learning problem for machine learning. Time Series Forecasting as Supervised Learning Photo by Jeroen Looyé, some rights reserved. The majority of practical machine learning uses supervised learning. Supervised learning is where you have input variables (X) and an output variable (y) and you use an algorithm to learn the mapping function from the input to the output.

Entity resolution (ER), an important and common data cleaning problem, is about detecting data duplicate representations for the same external entities, and merging them into single representations. Relatively recently, declarative rules called "matching dependencies" (MDs) have been proposed for specifying similarity conditions under which attribute values in database records are merged. In this work we show the process and the benefits of integrating four components of ER: (a) Building a classifier for duplicate/non-duplicate record pairs built using machine learning (ML) techniques; (b) Use of MDs for supporting the blocking phase of ML; (c) Record merging on the basis of the classifier results; and (d) The use of the declarative language "LogiQL" -an extended form of Datalog supported by the "LogicBlox" platform- for all activities related to data processing, and the specification and enforcement of MDs.

Radio emitter recognition in dense multi-user environments is an important tool for optimizing spectrum utilization, identifying and minimizing interference, and enforcing spectrum policy. Radio data is readily available and easy to obtain from an antenna, but labeled and curated data is often scarce making supervised learning strategies difficult and time consuming in practice. We demonstrate that semi-supervised learning techniques can be used to scale learning beyond supervised datasets, allowing for discerning and recalling new radio signals by using sparse signal representations based on both unsupervised and supervised methods for nonlinear feature learning and clustering methods.

This repository contains a 1st place solution for the Painter by Numbers competition on Kaggle. Below is a brief description of the dataset and approaches I've used to build and validate a predictive model. The challenge of the competition was to examine pairs of paintings and determine whether they were painted by the same artist. The training set consists of artwork images and their corresponding class labels (painters). Examples in the test set were split into 13 groups and all possible pairs within each group needed to be examined for the submission.

Techniques known as Nonlinear Set Membership prediction, Lipschitz Interpolation or Kinky Inference are approaches to machine learning that utilise presupposed Lipschitz properties to compute inferences over unobserved function values. Provided a bound on the true best Lipschitz constant of the target function is known a priori they offer convergence guarantees as well as bounds around the predictions. Considering a more general setting that builds on Hoelder continuity relative to pseudo-metrics, we propose an online method for estimating the Hoelder constant online from function value observations that possibly are corrupted by bounded observational errors. Utilising this to compute adaptive parameters within a kinky inference rule gives rise to a nonparametric machine learning method, for which we establish strong universal approximation guarantees. That is, we show that our prediction rule can learn any continuous function in the limit of increasingly dense data to within a worst-case error bound that depends on the level of observational uncertainty. We apply our method in the context of nonparametric model-reference adaptive control (MRAC). Across a range of simulated aircraft roll-dynamics and performance metrics our approach outperforms recently proposed alternatives that were based on Gaussian processes and RBF-neural networks. For discrete-time systems, we provide stability guarantees for our learning-based controllers both for the batch and the online learning setting.

We study the problem of 3D object generation. We propose a novel framework, namely 3D Generative Adversarial Network (3D-GAN), which generates 3D objects from a probabilistic space by leveraging recent advances in volumetric convolutional networks and generative adversarial nets. The benefits of our model are three-fold: first, the use of an adversarial criterion, instead of traditional heuristic criteria, enables the generator to capture object structure implicitly and to synthesize high-quality 3D objects; second, the generator establishes a mapping from a low-dimensional probabilistic space to the space of 3D objects, so that we can sample objects without a reference image or CAD models, and explore the 3D object manifold; third, the adversarial discriminator provides a powerful 3D shape descriptor which, learned without supervision, has wide applications in 3D object recognition. Experiments demonstrate that our method generates high-quality 3D objects, and our unsupervisedly learned features achieve impressive performance on 3D object recognition, comparable with those of supervised learning methods.

During the past few years, the machine learning community has paid attention to developping new methods for learning from weakly labeled data. This field covers different settings like semi-supervised learning, learning with label proportions, multi-instance learning, noise-tolerant learning, etc. This paper presents a generic framework to deal with these weakly labeled scenarios. We introduce the beta-risk as a generalized formulation of the standard empirical risk based on surrogate margin-based loss functions. This risk allows us to express the reliability on the labels and to derive different kinds of learning algorithms. We specifically focus on SVMs and propose a soft margin beta-svm algorithm which behaves better that the state of the art.