Having played a central role at the inception of artificial intelligence research, machine learning has recently reemerged as a major area of study at the very core of the subject. Solid theoretical foundations are being constructed. Machine learning methods are being integrated with powerful performance systems, and practical applications; based on established techniques are emerging.Machine Learning unifies the field by bringing together and clearly explaining the major successful paradigms for machine learning: inductive approaches, explanation-based learning, genetic algorithms, and connectionist learning methods. Each paradigm is presented in depth, providing historical perspective but focusing on current research and potential applications.

India and Pakistan have fought four wars in the past few decades, but when India faced an oxygen shortage in its hospitals during its recent COVID-19 surge, Pakistan offered to help. Finding these positive tweets, however, was not as easy as simply browsing the supportive hashtags or looking at the most popular posts. And Twitter's algorithm isn't tuned to surface the most positive tweets during a crisis. Ashique KhudaBukhsh of Carnegie Mellon University's Language Technologies Institute led a team of researchers who used machine learning to identify supportive tweets from Pakistan during India's COVID crisis. In the throes of a public health crisis, words of hope can be welcome medicine.

The cost of annotating training data has traditionally been a bottleneck for supervised learning approaches. The problem is further exacerbated when supervised learning is applied to a number of correlated tasks simultaneously since the amount of labels required scales with the number of tasks. To mitigate this concern, we propose an active multitask learning algorithm that achieves knowledge transfer between tasks. The approach forms a so-called committee for each task that jointly makes decisions and directly shares data across similar tasks. Our approach reduces the number of queries needed during training while maintaining high accuracy on test data. Empirical results on benchmark datasets show significant improvements on both accuracy and number of query requests.

Machine Learning has bcrn a constant, theme t,hroughout AI's two decades of existence In this ovcrview t,hc authors analyze various aspects including the major met,hodological approaches advocated in Machine Learning research, Machine learning has always been an integral part of artificial intelligcncc, and it.s This paper is a modified and extended version of the first chapt.er of Machine Learnznq, An Artijicrul Intelligence Approach, with per mission of the publisher: Tioga Press (Palo Alto, Ch) The research described here was sponsored in palt, by the Office of Naval & scar& More recently, new symbolic met,hods and knowledge-intcnsivc techniques have yielded promising results and these in t.urn have led to the current, revival in machine lcwrning research This article examines some basic methodological issues, proposes a classification of machine learning techniques, and provides a historical review of t,he major research directions The Objectives of Machine Learning The field of machine learning can bc organized around three primary research foci: At, present, itisi ructing a cotnJnit,er or a computer-controlled robot, to perform a t,ask requires one t,o define a comple1.e and correct, algoril,hm for that. Prcsrnt-day computer systeitis cannot truly learn to J)erform a La& through exa1nJ)lcs or by analogy Lo a similar, J)rcviously-solved t,ask. Nor can they improve significantly on t,lle basis of)asl, tnistakes, or acquire new abilities l)y observing and itnit,ating exJ)erts Macllinc learning research strives to open IShe possibility of instructing computers in such new ways, and t.liereby promises Lo ease lhe burden of hand-progratnmirlg growing volutttes of increasingly coniplcx informat ioti into lhe computers of t.omorrow. The t,raditiotlal argumenl that an cnginecring approacll need not reflect human or biological J)erformanc:c is not, truly applicable t,o tuachine learning.

As evidenced by the articles in this special issue, transfer learning has come a long way in the past five or so years, partially because of DARPA's Transfer Learning program, which sponsored much of the work reported in this issue. There is a Transfer Learning Toolkit for Matlab available on the web. Transfer learning has developed techniques for classification, regression, and clustering (as summarized in Pan and Yang's 2009 survey) and for complex interactive tasks that are often best addressed by reinforcement learning techniques. However, there is a more practical and more feasible goal for transfer learning against which progress is being made. An engineering-oriented goal of artificial intelligence that could be enabled by transfer learning is the ability to construct a large number of diverse applications not from scratch, but by taking advantage of knowledge already acquired and formally represented for other purposes.

AI research at CMU is closely integrated with other activities in the Computer Science Department, and to a major degree with ongoing research in the Psychology Department. Although there are over 50 faculty, staff and graduate students involved in various aspects of AI research, there is no administratively (or physically) separate AI laboratory. To underscore the interdisciplinary nature of much of our AI research, a significant fraction of the projects listed below are joint ventures between computer science and psychology. The history of AI research at Carnegie-Mellon goes back twenty-five years. The early work was characterized by a focus on problem solving and by interaction with psychology.

And now, AI invades the skies. Algorithms are learning to predict delays, giving airports and airlines a better shot at avoiding them. Airlines like EasyJet and Emirates are using the tech to remake the ticketing process painless and turn the in-flight experience into a personalized joy. But the true promise sits in the cockpit, where AI autopilots could help manage the complex airline operations and even respond to the millisecond-urgency of unfolding cockpit crises. Research here is young but developing quickly.

A new partnership between aviation giant Boeing and Carnegie Mellon University hints at the power of fields such as artificial intelligence and big data to transform huge, multi-billion-dollar industries. As part of a three-year, $7.5 million deal that will establish a new Aerospace Data Analytics Lab, Boeing and the Carnegie Mellon School of Computer Science will work on a range of new projects that will apply the principles of AI and big data to improving the quality of Boeing's aerospace activities. The goal of the new partnership, first and foremost is to make sense of the burgeoning amount of data in the aerospace industry. By applying principles of machine learning, it might be possible to optimize many aspects of Boeing's operations -- including those related to design, construction and operation – and turn ordinary data into real-world insights. According to Jaime Carbonell, the Carnegie Mellon professor and Director of the Language Technologies Institute, who will head up the new Aerospace Data Analytics Lab, "The mass of data generated daily by the aerospace industry overwhelms human understanding, but recent advances in language technologies and machine learning give us every reason to expect that we can gain useful insights from that data."

Running software that took four years and millions of dollars to develop, Carbonell's machine – or rather, the server farm it's connected to a few miles away – is attempting a task that has bedeviled computer scien tists for half a century. The message isn't encrypted or scrambled or hidden among thousands of documents. I brought along the text, taken from a Spanish newspaper transcript of a 2004 al Qaeda video claiming responsibility for the Madrid train bombings, to test Meaningful Machines' automated translation software. The brainchild of a quirky former used-car salesman named Eli Abir, the company has been designing the system in secret since just after 9/11. Now the application is ready for public scrutiny, on the heels of a research paper that Carbonell – who is also a professor of computer science at Carnegie Mellon University and head of the school's Language Technologies Institute – presented at a conference this summer. In it, he asserts that the company's software represents not only the most accurate Spanish-to-English translation system ever created but also a major advance in the field of machine translation. This article has been reproduced in a new format and may be missing content or contain faulty links.

Below is the uncorrected machine-read text of this chapter, intended to provide our own search engines and external engines with highly rich, chapter-representative searchable text of each book. Because it is UNCORRECTED material, please consider the following text as a useful but insufficient proxy for the authoritative book pages. For eons they have carried out a huge variety of tasks, from manufacturing goods, to transporting people around, to helping us decipher the natural world, to simply entertaining us. Machines can fight, protect, heal, and even teach us. But what they have not been able to do until quite recently is to learn, make decisions, and act on their own. Today, intelligent machines are everywhere. From the Netflix recommendation en- gine to Google Translate to Appleâ s Siri voice-recognition system, artificial intelligence has become sufficiently accurate, reliable, and useful to find its way into numerous devices and applications. These technologies have taken off in parallel with a dramatic expan- sion of the amount and complexity of data, which provides fertile teaching ground from which machines can learn to make intelligent decisions on their own.