Existing deep multitask learning (MTL) approaches align layers shared between tasks in a parallel ordering. Such an organization significantly constricts the types of shared structure that can be learned. The necessity of parallel ordering for deep MTL is first tested by comparing it with permuted ordering of shared layers. The results indicate that a flexible ordering can enable more effective...

Editor's Note: These short, critical reviews of recent papers in the Journal, written exclusively by graduate students or postdoctoral fellows, are intended to summarize the important findings of the paper and provide additional insight and commentary. For more information on the format and purpose of the Journal Club, please see The role of the medial temporal lobes (MTLs) in memory was first ...

A functional segregation along the posterior-anterior axis of the medial temporal lobe (MTL) has been suggested. In brief, it is thought that the posterior hippocampus represents environmental detail and/or encodes space, whereas the anterior part represents the environment more as a whole and/or subserves behavior. Different phases of navigation should thus recruit different structures within ...

We investigate the satisfiability problem for metric temporal logic (MTL) with both past and future operators over linear discrete bi-infinite time models — where time is unbounded both in the future and in the past — isomorphic to the integer numbers. We provide a technique to reduce satisfiability over the integers to satisfiability over the well-known mono-infinite time model of natural numb...

Ability to count number of occurrences of events within a specified time interval is very useful in specification of resource bounded real time computation. In this paper, we study an extension of Metric Temporal Logic (MTL) with two different counting modalities called C and UT (until with threshold), which enhance the expressive power of MTL in orthogonal fashion. We confine ourselves only to...

Pathology at preclinical and prodromal stages of Alzheimer's disease (AD) may manifest itself as measurable functional change in neuronal networks earlier than detectable structural change. Functional connectivity as measured using resting-state functional magnetic resonance imaging has emerged as a useful tool for studying disease effects on baseline states of neuronal networks. In this study,...

Neurons in the medial temporal lobe (MTL), a critical area for declarative memory, have been shown to change their tuning in associative learning tasks. Yet, it is unclear how durable these neuronal representations are and if they outlast the execution of the task. To address this issue, we studied the responses of MTL neurons in neurosurgical patients to known concepts (people and places). Usi...

Associative memory is defined as memory for the relationship between two initially unrelated items, like a name and an unfamiliar face. Associative memory is not only one of the most common forms of memory used in everyday situations, but is highly dependent on the structures of the medial temporal lobe (MTL). The goal of this chapter is to review the patterns of neural activity shown to underl...

Enhanced memory for emotional faces is a significant component of adaptive social interactions, but little is known on its neural developmental correlates. We explored the role of amygdaloid complex (AC) and medial temporal lobe (MTL) in emotional memory recognition across development, by comparing fMRI activations of successful memory encoding of fearful and neutral faces in children (n = 12; ...

Despite the recent progress in speech emotion recognition (SER), state-of-the-art systems lack generalisation across different conditions. A key underlying reason for poor is scarcity of datasets, which a significant roadblock to designing robust machine learning (ML) models. Recent works SER focus on utilising multitask (MTL) methods improve by shared representations. However, most these studi...