Multiple task learning (MTL) neural networks are one of the better documented methods of inductive transfer of task knowledge (Caruana 1997). An MTL network is a feedforward multi-layer network with an output node for each task being learned. The standard back-propagation of error learning algorithm is used to train all tasks in parallel. The sharing of internal representation in the hidden nod...

We consider the control problem for timed automata against specifications given as MTL formulas. The logic MTL is a linear-time timed temporal logic which extends LTL with timing constraints on modalities, and recently, its model-checking has been proved decidable in several cases. We investigate these decidable fragments of MTL (full MTL when interpreted over finite timed words, and Safety-MTL...

The striatum and connected cortical areas have been implicated in sequence learning (SL) tasks, in which performance increments are gradual and learning typically occurs in the absence of awareness. It has recently been shown that increasing striatal activation during SL may be accompanied by decreasing activation in the medial temporal lobe (MTL) across time, but the specific contribution of t...

The problem of multi-task learning (MTL) is considered for sequential data, such as that typically modeled via a hidden Markov model (HMM). A given task is composed of a set of sequential data, for which an HMM is to be learned, and MTL is employed to learn the multiple task-dependent HMMs jointly, through appropriate sharing of data. The HMM-MTL formulation is implemented in a Bayesian setting...

The selective transfer of task knowledge within the context of artificial neural networks is studied in the MTL learning framework, a modified version of the multiple task learning (MTL) method of functional transfer. MTL is a knowledge based inductive learning system that uses prior task knowledge to adjust its inductive bias. MTL employs a separate learning rate for each task output node. The...

The mating type locus (MTL) of Candida albicans contains the mating type genes and has, therefore, been assumed to play an exclusive role in the mating process. In mating-incompetent a/α cells, two of the mating type genes, MTLa1 and MTLα2, encode components of the a1-α2 corepressor that suppresses mating and switching. But the MTL locus of C. albicans also contains three apparently unrelated "...

High-resolution functional MRI (hr-fMRI) affords unique leverage on the functional properties of human medial temporal lobe (MTL) substructures. We review initial hr-fMRI efforts to delineate (1) encoding and retrieval processes within the hippocampal circuit, (2) hippocampal subfield contributions to pattern separation and pattern completion, and (3) the representational capabilities of distin...

The involvement of retrosplenial cortex (RSC) in human autobiographical memory retrieval has been confirmed by functional brain imaging studies, and is supported by anatomical evidence of strong connectivity between the RSC and memory structures within the medial temporal lobe (MTL). However, electrophysiological investigations of the RSC and its interaction with the MTL have mostly remained li...

OBJECTIVES/HYPOTHESIS To investigate the clinical significance of middle turbinate lateralization (MTL) occurrence postendoscopic sinus surgery (ESS) for chronic rhinosinusitis, namely, association with postoperative symptoms and eventual need for undergoing revision surgery. STUDY DESIGN Retrospective chart review of consecutive postoperative follow-up appointments (November 2009-May 2011) f...

Decoding models based on pattern recognition (PR) are becoming increasingly important tools for neuroimaging data analysis. In contrast to alternative (mass-univariate) encoding approaches that use hierarchical models to capture inter-subject variability, inter-subject differences are not typically handled efficiently in PR. In this work, we propose to overcome this problem by recasting the dec...