Multi-task learning (MTL) can be an effective way to improve the generalization performance of singly learning tasks if the tasks are related, especially when the amount of training data is small. Our previous work applied MTL to the joint training of triphone and trigrapheme acoustic models using deep neural networks (DNNs) for low-resource speech recognition. Significant recognition improveme...

Medial temporal lobe (MTL) function is well established as necessary for memory of facts and events. It is likely that lateral cortical regions critically guide cognitive control processes to tune in high-fidelity details that are most relevant for memory retrieval. Here, convergent results from functional and structural MRI show that retrieval of detailed episodic memory arises from lateral co...

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...

Damage to the medial temporal lobe (MTL) has long been known to impair declarative memory, and recent evidence suggests that it also impairs visual perception. A theory termed the representational-hierarchical account explains such impairments by assuming that MTL stores conjunctive representations of items and events, and that individuals with MTL damage must rely upon representations of simpl...

Early studies of memory-impaired patients with medial temporal lobe (MTL) damage led to the view that the hippocampus and related MTL structures are involved in the formation of long-term memory and that immediate memory and working memory are independent of these structures. This traditional idea has recently been revisited. Impaired performance in patients with MTL lesions on tasks with short...

In the context of real-time systems, Metric Temporal Logic (MTL) and Timed Propositional Temporal Logic (TPTL) are prominent and widely used extensions of Linear Temporal Logic. In this paper, we examine the possibility of using MTL and TPTL to specify properties about classes of non-monotonic data languages over the natural numbers. Words in this class may model the behaviour of, e.g., one-cou...

In this paper, we provide a Dynamic Programming algorithm for online monitoring of the state robustness of Metric Temporal Logic specifications with past time operators. We compute the robustness of MTL with unbounded past and bounded future temporal operators (MTL<+∞ +pt ) over sampled traces of Cyber-Physical Systems. We implemented our tool in Matlab as a Simulink block that can be used in a...

We study modal team logic MTL and the dependence-free fragment FO2[∼] of two-variable team logic, which extend modal logic ML and two-variable logic FO2 with team semantics by a Boolean negation ∼. We settle the open question of the complexity of their respective satisfiability problems, and prove that both are complete for a non-elementary complexity class. We also prove that the model checkin...

BACKGROUND Myasthenia gravis (MG) is occasionally aggravated by chronic infection, of which there are many kinds. CASE REPORT We report herein the case of a 56-year-old woman with MG aggravated by the activation of isolated mediastinal tuberculous lymphadenitis (MTL) during corticosteroid administration. The possibility of MTL had been disregarded in the differential diagnosis of aggravation ...

This paper proposes the meeting of fuzzy logic with paraconsistency in a very precise and foundational way. Specifically, in this paper we introduce expansions of the fuzzy logic MTL by means of primitive operators for consistency and inconsistency in the style of the so-called Logics of Formal Inconsistency (LFIs). The main novelty of the present approach is the definition of postulates for th...