Methamphetamine affects the hippocampus, a brain region crucial for learning and memory, as well as relapse to drug seeking. Rats self-administered methamphetamine for 1 h twice weekly (intermittent-short-I-ShA), 1 h daily (limited-short-ShA), or 6 h daily (extended-long-LgA) for 22 sessions. After 22 sessions, rats from each access group were withdrawn from self-administration and underwent spatial memory (Y-maze) and working memory (T-maze) tests followed by extinction and reinstatement to methamphetamine seeking or received one intraperitoneal injection of 5-bromo-2'-deoxyuridine (BrdU) to label progenitors in the hippocampal subgranular zone (SGZ) during the synthesis phase. Two-hour-old and 28-day-old surviving BrdU-immunoreactive cells were quantified. I-ShA rats performed better on the Y-maze and had a greater number of 2-h-old SGZ BrdU cells than nondrug controls. LgA rats, but not ShA rats, performed worse on the Y- and T-maze and had a fewer number of 2-h-old SGZ BrdU cells than nondrug and I-ShA rats, suggesting that new hippocampal progenitors, decreased by methamphetamine, were correlated with impairment in the acquisition of new spatial cues. Analyses of addiction-related behaviors after withdrawal and extinction training revealed methamphetamine-primed reinstatement of methamphetamine-seeking behavior in all three groups (I-ShA, ShA, and LgA), and this effect was enhanced in LgA rats compared with I-ShA and ShA rats. Protracted withdrawal from self-administration enhanced the survival of SGZ BrdU cells, and methamphetamine seeking during protracted withdrawal enhanced Fos expression in the dentate gyrus and medial prefrontal cortex in LgA rats to a greater extent than in ShA and I-ShA rats. These results indicate that changes in the levels of the proliferation and survival of hippocampal neural progenitors and neuronal activation of hippocampal granule cells predict the effects of methamphetamine self-administration (limited vs extended access) on cognitive performance and relapse to drug seeking and may contribute to the impairments that perpetuate the addiction cycle.

No abstract

The volume of energy loss that Brazilian electric utilities have to deal with has been ever increasing. The electricity concessionaries are suffering significant and increasing loss in the last years, due to theft, measurement errors and many other kinds of irregularities. Therefore, there is a great concern from those companies to identify the profile of irregular customers, in order to reduce the volume of such losses. This paper presents the proposal of an intelligent system, composed of two neural networks ensembles, which intends to increase the level of accuracy in the identification of irregularities among low tension consumers. The data used to test the proposed system are from Light S.A. Company, the Rio de Janeiro concessionary. The results obtained presented a significant increase in the identification of irregular customers when compared to the current methodology employed by the company.

Objectives: Accurately stratifying patients in the preoperative period according to mortality risk informs treatment considerations and guides adjustments to bundled reimbursements. We developed and compared three machine learning models to determine which best predicts 30-day mortality after hip fracture. Methods: The 2016 to 2017 National Surgical Quality Improvement Program for hip fracture (AO/OTA 31-A-B-C) procedure-targeted data were analyzed. Three models—artificial neural network, naive Bayes, and logistic regression—were trained and tested using independent variables selected via backward variable selection. The data were split into 80% training and 20% test sets. Predictive accuracy between models was evaluated using area under the curve receiver operating characteristics. Odds ratios were determined using multivariate logistic regression with P < 0.05 for significance. Results: The study cohort included 19,835 patients (69.3% women). The 30-day mortality rate was 5.3%. In total, 47 independent patient variables were identified to train the testing models. Area under the curve receiver operating characteristics for 30-day mortality was highest for artificial neural network (0.92), followed by the logistic regression (0.87) and naive Bayes models (0.83). Discussion: Machine learning is an emerging approach to develop accurate risk calculators that account for the weighted interactions between variables. In this study, we developed and tested a neural network model that was highly accurate for predicting 30-day mortality after hip fracture. This was superior to the naive Bayes and logistic regression models. The role of machine learning models to predict orthopaedic outcomes merits further development and prospective validation but shows strong promise for positively impacting patient care.

No abstract

We present memory-efficient and scalable algorithms for kernel methods used in machine learning. Using hierarchical matrix approximations for the kernel matrix the memory requirements, the number of floating point operations, and the execution time are drastically reduced compared to standard dense linear algebra routines. We consider both the general H matrix hierarchical format as well as Hierarchically Semi-Separable (HSS) matrices. Furthermore, we investigate the impact of several preprocessing and clustering techniques on the hierarchical matrix compression. Effective clustering of the input leads to a ten-fold increase in efficiency of the compression. The algorithms are implemented using the STRUMPACK solver library. These results confirm that -with correct tuning of the hyperparameters -classification using kernel ridge regression with the compressed matrix does not lose prediction accuracy compared to the exact -not compressed -kernel matrix and that our approach can be extended to O(1M ) datasets, for which computation with the full kernel matrix becomes prohibitively expensive. We present numerical experiments in a distributed memory environment up to 1,024 processors of the NERSC's Cori supercomputer using wellknown datasets to the machine learning community that range from dimension 8 up to 784.

We present Accelerated Cyclic Reduction (ACR), a distributed-memory fast solver for rank-compressible block tridiagonal linear systems arising from the discretization of elliptic operators, developed here for three dimensions. Algorithmic synergies between Cyclic Reduction and hierarchical matrix arithmetic operations result in a solver that has Opk N log N plog N`k 2 qq arithmetic complexity and Opk N log N q memory footprint, where N is the number of degrees of freedom and k is the rank of a block in the hierarchical approximation, and which exhibits substantial concurrency. We provide a baseline for performance and applicability by comparing with the multifrontal method with and without hierarchical semi-separable matrices, with algebraic multigrid and with the classic cyclic reduction method. Over a set of large-scale elliptic systems with features of nonsymmetry and indefiniteness, the robustness of the direct solvers extends beyond that of the multigrid solver, and relative to the multifrontal approach ACR has lower or comparable execution time and size of the factors, with substantially lower numerical ranks. ACR exhibits good strong and weak scaling in a distributed context and, as with any direct solver, is advantageous for problems that require the solution of multiple right-hand sides. Numerical experiments show that the rank k patterns are of Op1q for the Poisson equation and of Opnq for the indefinite Helmholtz equation. The solver is ideal in situations where low-accuracy solutions are sufficient, or otherwise as a preconditioner within an iterative method.

We present new algorithms for randomized construction of hierarchically semiseparable matrices, addressing several practical issues. The HSS construction algorithms use a partially matrix-free, adaptive randomized projection scheme to determine the maximum off-diagonal block rank. We develop both relative and absolute stopping criteria to determine the minimum dimension of the random projection matrix that is sufficient for desired accuracy. Two strategies are discussed to adaptively enlarge the random sample matrix: repeated doubling of the number of random vectors, and iteratively incrementing the number of random vectors by a fixed number. The relative and absolute stopping criteria are based on probabilistic bounds for the Frobenius norm of the random projection of the Hankel blocks of the input matrix. We discuss parallel implementation and computation and communication cost of both variants. Parallel numerical results for a range of applications, including boundary element method matrices and quantum chemistry Toeplitz matrices, show the effectiveness, scalability and numerical robustness of the proposed algorithms.