Carnegie Mellon University

About: Carnegie Mellon University is a education organization based out in Pittsburgh, Pennsylvania, United States. It is known for research contribution in the topics: Computer science & Robot. The organization has 36317 authors who have published 104359 publications receiving 5975734 citations. The organization is also known as: CMU & Carnegie Mellon.

The Mythos of Model Interpretability

Abstract: Supervised machine learning models boast remarkable predictive capabilities. But can you trust your model? Will it work in deployment? What else can it tell you about the world? We want models to be not only good, but interpretable. And yet the task of interpretation appears underspecified. Papers provide diverse and sometimes non-overlapping motivations for interpretability, and offer myriad notions of what attributes render models interpretable. Despite this ambiguity, many papers proclaim interpretability axiomatically, absent further explanation. In this paper, we seek to refine the discourse on interpretability. First, we examine the motivations underlying interest in interpretability, finding them to be diverse and occasionally discordant. Then, we address model properties and techniques thought to confer interpretability, identifying transparency to humans and post-hoc explanations as competing notions. Throughout, we discuss the feasibility and desirability of different notions, and question the oft-made assertions that linear models are interpretable and that deep neural networks are not.

What one intelligence test measures: A theoretical account of the processing in the Raven Progressive Matrices Test

Abstract: The cognitive processes in a widely used, nonverbal test of analytic intelligence, the Raven Progressive Matrices Test (Raven, 1962), are analyzed in terms of which processes distinguish between higher scoring and lower scoring subjects and which processes are common to all subjects and all items on the test. The analysis is based on detailed performance characteristics, such as verbal protocols, eye-fixation patterns, and errors. The theory is expressed as a pair of computer simulation models that perform like the median or best college students in the sample. The processing characteristic common to all subjects is an incremental, reiterative strategy for encoding and inducing the regularities in each problem. The processes that distinguish among individuals are primarily the ability to induce abstract relations and the ability to dynamically manage a large set of problem-solving goals in working memory.

The Hearsay-II Speech-Understanding System: Integrating Knowledge to Resolve Uncertainty

Abstract: The Hearsay-II system, developed during the DARPA-sponsored five-year speech-understanding research program, represents both a specific solution to the speech-understanding problem and a general framework for coordinating independent processes to achieve cooperative problem-solving behavior. As a computational problem, speech understanding reflects a large number of intrinsically interesting issues. Spoken sounds are achieved by a long chain of successive transformations, from intentions, through semantic and syntactic structuring, to the eventually resulting audible acoustic waves. As a consequence, interpreting speech means effectively inverting these transformations to recover the speaker's intention from the sound. At each step in the interpretive process, ambiguity and uncertainty arise. The Hearsay-II problem-solving framework reconstructs an intention from hypothetical interpretations formulated at various levels of abstraction. In addition, it allocates limited processing resources first to the most promising incremental actions. The final configuration of the Hearsay-II system comprises problem-solving components to generate and evaluate speech hypotheses, and a focus-of-control mechanism to identify potential actions of greatest value. Many of these specific procedures reveal novel approaches to speech problems. Most important, the system successfully integrates and coordinates all of these independent activities to resolve uncertainty and control combinatorics. Several adaptations of the Hearsay-II framework have already been undertaken in other problem domains, and it is anticipated that this trend will continue; many future systems necessarily will integrate diverse sources of knowledge to solve complex problems cooperatively. Discussed in this paper are the characteristics of the speech problem in particular, the special kinds of problem-solving uncertainty in that domain, the structure of the Hearsay-II system developed to cope with that uncertainty, and the relationship between Hearsay-II's structure and those of other speech-understanding systems. The paper is intended for the general computer science audience and presupposes no speech or artificial intelligence background.

Limits on super-resolution and how to break them

Abstract: Nearly all super-resolution algorithms are based on the fundamental constraints that the super-resolution image should generate low resolution input images when appropriately warped and down-sampled to model the image formation process. (These reconstruction constraints are normally combined with some form of smoothness prior to regularize their solution.) We derive a sequence of analytical results which show that the reconstruction constraints provide less and less useful information as the magnification factor increases. We also validate these results empirically and show that, for large enough magnification factors, any smoothness prior leads to overly smooth results with very little high-frequency content. Next, we propose a super-resolution algorithm that uses a different kind of constraint in addition to the reconstruction constraints. The algorithm attempts to recognize local features in the low-resolution images and then enhances their resolution in an appropriate manner. We call such a super-resolution algorithm a hallucination or reconstruction algorithm. We tried our hallucination algorithm on two different data sets, frontal images of faces and printed Roman text. We obtained significantly better results than existing reconstruction-based algorithms, both qualitatively and in terms of RMS pixel error.

Situated Learning and Education

Abstract: This paper provides a review of the claims of situated learning that are having an increasing influence on education generally and mathematics education particularly. We review the four central claims of situated learning with respect to education: (1) action is grounded in the concrete situation in which it occurs; (2) knowledge does not transfer between tasks; (3) training by abstraction is of little use; and (4) instruction must be done in complex, social environments. In each case, we cite empirical literature to show that the claims are overstated and that some of the educational implications that have been taken from these claims are misguided.