Harnessing the statistical power of neural networks to perform language understanding and symbolic reasoning is difficult, when it requires executing efficient discrete operations against a large knowledge-base. In this work, we introduce a Neural Symbolic Machine (NSM), which contains (a) a neural "programmer", i.e., a sequence-to-sequence model that maps language utterances to programs and utilizes a key-variable memory to handle compositionality (b) a symbolic "computer", i.e., a Lisp interpreter that performs program execution, and helps find good programs by pruning the search space. We apply REINFORCE to directly optimize the task reward of this structured prediction problem. To train with weak supervision and improve the stability of REINFORCE we augment it with an iterative maximum-likelihood training process. NSM outperforms the state-of-theart on the WEBQUESTIONSSP dataset when trained from question-answer pairs only, without requiring any feature engineering or domain-specific knowledge.
Machine learning, particularly deep learning has boosted medical image analysis over the past years. Training a good model based on deep learning requires large amount of labelled data. However, it is often difficult to obtain a sufficient number of labelled images for training. In many scenarios the dataset in question consists of more unlabelled images than labelled ones. Therefore, boosting the performance of machine learning models by using unlabelled as well as labelled data is an important but challenging problem. Self-supervised learning presents one possible solution to this problem. However, existing self-supervised learning strategies applicable to medical images cannot result in significant performance improvement. Therefore, they often lead to only marginal improvements. In this paper, we propose a novel self-supervised learning strategy based on context restoration in order to better exploit unlabelled images. The context restoration strategy has three major features: 1) it learns meaningful image semantics; 2) it is useful for different types of subsequent image analysis tasks; and 3) its implementation is simple. We validate the context restoration strategy in three common problems in medical imaging: classification, localization, and segmentation. For classification, we apply and test it to scan plane detection in fetal 2D ultrasound images; to localise abdominal organs in CT images; and to segment brain tumours in multi-modal MR images. In all three cases, self-supervised learning based on context restoration learns meaningful semantic features and lead to improved machine learning models for the above tasks.
Neuronal activity in the brain reflects an excitation–inhibition balance that is regulated predominantly by glutamatergic and GABAergic neurotransmission, and often disturbed in neuropsychiatric disorders. Here, we tested the effects of a single oral dose of two anti-glutamatergic drugs (dextromethorphan, an NMDA receptor antagonist; perampanel, an AMPA receptor antagonist) and an L-type voltage-gated calcium channel blocker (nimodipine) on transcranial magnetic stimulation (TMS)-evoked electroencephalographic (EEG) potentials (TEPs) and TMS-induced oscillations (TIOs) in 16 healthy adults in a pseudorandomized, double-blinded, placebo-controlled crossover design. Single-pulse TMS was delivered to the hand area of left primary motor cortex. Dextromethorphan increased the amplitude of the N45 TEP, while it had no effect on TIOs. Perampanel reduced the amplitude of the P60 TEP in the non-stimulated hemisphere, and increased TIOs in the beta-frequency band in the stimulated sensorimotor cortex, and in the alpha-frequency band in midline parietal channels. Nimodipine and placebo had no effect on TEPs and TIOs. The TEP results extend previous pharmaco-TMS-EEG studies by demonstrating that the N45 is regulated by a balance of GABAAergic inhibition and NMDA receptor-mediated glutamatergic excitation. In contrast, AMPA receptor-mediated glutamatergic neurotransmission contributes to propagated activity reflected in the P60 potential and midline parietal induced oscillations. This pharmacological characterization of TMS-EEG responses will be informative for interpreting TMS-EEG abnormalities in neuropsychiatric disorders with pathological excitation–inhibition balance.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.