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.

Symbolic model checking: 10/sup 20/ states and beyond

Abstract: A general method that represents the state space symbolically instead of explicitly is described. The generality of the method comes from using a dialect of the mu-calculus as the primary specification language. A model-checking algorithm for mu-calculus formulas which uses R.E. Bryant's (1986) binary decision diagrams to represent relations and formulas symbolically is described. It is then shown how the novel mu-calculus model checking algorithm can be used to derive efficient decision procedures for CTL model checking, satisfiability of linear-time temporal logic formulas, strong and weak observational equivalence of finite transition systems, and language containment of finite omega -automata. This eliminates the need to describe complicated graph-traversal or nested fixed-point computations for each decision procedure. The authors illustrate the practicality of their approach to symbolic model checking by discussing how it can be used to verify a simple synchronous pipeline. >

The Cascade-Correlation Learning Architecture

Abstract: Cascade-Correlation is a new architecture and supervised learning algorithm for artificial neural networks. Instead of just adjusting the weights in a network of fixed topology. Cascade-Correlation begins with a minimal network, then automatically trains and adds new hidden units one by one, creating a multi-layer structure. Once a new hidden unit has been added to the network, its input-side weights are frozen. This unit then becomes a permanent feature-detector in the network, available for producing outputs or for creating other, more complex feature detectors. The Cascade-Correlation architecture has several advantages over existing algorithms: it learns very quickly, the network determines its own size and topology, it retains the structures it has built even if the training set changes, and it requires no back-propagation of error signals through the connections of the network.

Shape and motion from image streams under orthography: a factorization method

Abstract: Inferring scene geometry and camera motion from a stream of images is possible in principle, but is an ill-conditioned problem when the objects are distant with respect to their size. We have developed a factorization method that can overcome this difficulty by recovering shape and motion under orthography without computing depth as an intermediate step. An image stream can be represented by the 2FxP measurement matrix of the image coordinates of P points tracked through F frames. We show that under orthographic projection this matrix is of rank 3. Based on this observation, the factorization method uses the singular-value decomposition technique to factor the measurement matrix into two matrices which represent object shape and camera rotation respectively. Two of the three translation components are computed in a preprocessing stage. The method can also handle and obtain a full solution from a partially filled-in measurement matrix that may result from occlusions or tracking failures. The method gives accurate results, and does not introduce smoothing in either shape or motion. We demonstrate this with a series of experiments on laboratory and outdoor image streams, with and without occlusions.

Positive Events and Social Supports as Buffers of Life Change Stress

Abstract: A perceived availability of social support measure (the ISEL) was designed with independent subscales measuring four separate support functions. In a sample of college students, both perceived availability of social support and number of positive events moderated the relationship between negative life stress and depressive and physical symptomatology. In the case of depressive symptoms, the data fit a “buffering” hypothesis pattern, i.e., they suggest that both social support and positive events protect one from the pathogenic effects of high levels of life stress but are relatively unimportant for those with low levels of stress. In the case of physical symptoms, the data only partially support the buffering hypothesis. Particularly, the data suggest that both social support and positive events protect one from the pathogenic effects of high levels of stress but harm those (i.e., are associated with increased symptomatology) with low levels of stress. Further analyses suggest that self-esteem and appraisal support were primarily responsible for the reported interactions between negative life stress and social support. In contrast, frequency of past social support was not an effective life stress buffer in either the case of depressive or physical symptomatology. Moreover, past support frequency was positively related to physical symptoms and unrelated to depressive symptoms, while perceived availability of support was negatively related to depressive symptoms and unrelated to physical symptoms.

Convolutional Pose Machines

Abstract: Pose Machines provide a sequential prediction framework for learning rich implicit spatial models. In this work we show a systematic design for how convolutional networks can be incorporated into the pose machine framework for learning image features and image-dependent spatial models for the task of pose estimation. The contribution of this paper is to implicitly model long-range dependencies between variables in structured prediction tasks such as articulated pose estimation. We achieve this by designing a sequential architecture composed of convolutional networks that directly operate on belief maps from previous stages, producing increasingly refined estimates for part locations, without the need for explicit graphical model-style inference. Our approach addresses the characteristic difficulty of vanishing gradients during training by providing a natural learning objective function that enforces intermediate supervision, thereby replenishing back-propagated gradients and conditioning the learning procedure. We demonstrate state-of-the-art performance and outperform competing methods on standard benchmarks including the MPII, LSP, and FLIC datasets.