Over the last decade, substantial advances have been made in various computer vision technologies and many of them are based on convolutional neural network (CNN) architecture. Typically, CNN is ...trained by a stochastic gradient descent algorithm using Back-Propagation (BP) but the training process is adversely affected by slow convergence and the need for extensive parameter tuning. In this paper, we propose a new CNN architecture and training algorithm based on an Extreme Learning Machine (ELM) to overcome these drawbacks. The proposed training algorithm is a layer-wise training method for CNN, and uses an alternating strategy of random convolutional filters and semi-supervised filters to combine the advantages of both approaches. On each semi-supervised layer, the CNN efficiently solves a convex optimization problem based on nonlinear random projection. It is faster and requires less human effort than BP-based training. We experimentally validated the proposed method using a well-known character and object recognition benchmark. In our experiment, the performance of our method is comparable to approaches based on deep features and has higher accuracy than other unsupervised feature-learning methods.
Recent advances in coupled oscillator theory Ermentrout, Bard; Park, Youngmin; Wilson, Dan
Philosophical transactions of the Royal Society of London. Series A: Mathematical, physical, and engineering sciences,
12/2019, Letnik:
377, Številka:
2160
Journal Article
Recenzirano
Odprti dostop
We review the theory of weakly coupled oscillators for smooth systems. We then examine situations where application of the standard theory falls short and illustrate how it can be extended. Specific ...examples are given to non-smooth systems with applications to the Izhikevich neuron. We then introduce the idea of isostable reduction to explore behaviours that the weak coupling paradigm cannot explain. In an additional example, we show how bifurcations that change the stability of phase-locked solutions in a pair of identical coupled neurons can be understood using the notion of isostable reduction. This article is part of the theme issue 'Coupling functions: dynamical interaction mechanisms in the physical, biological and social sciences'.
A circuit model of auditory cortex Park, Youngmin; Geffen, Maria N
PLoS computational biology,
07/2020, Letnik:
16, Številka:
7
Journal Article
Recenzirano
Odprti dostop
The mammalian sensory cortex is composed of multiple types of inhibitory and excitatory neurons, which form sophisticated microcircuits for processing and transmitting sensory information. Despite ...rapid progress in understanding the function of distinct neuronal populations, the parameters of connectivity that are required for the function of these microcircuits remain unknown. Recent studies found that two most common inhibitory interneurons, parvalbumin- (PV) and somatostatin-(SST) positive interneurons control sound-evoked responses, temporal adaptation and network dynamics in the auditory cortex (AC). These studies can inform our understanding of parameters for the connectivity of excitatory-inhibitory cortical circuits. Specifically, we asked whether a common microcircuit can account for the disparate effects found in studies by different groups. By starting with a cortical rate model, we find that a simple current-compensating mechanism accounts for the experimental findings from multiple groups. They key mechanisms are two-fold. First, PVs compensate for reduced SST activity when thalamic inputs are strong with less compensation when thalamic inputs are weak. Second, SSTs are generally disinhibited by reduced PV activity regardless of thalamic input strength. These roles are augmented by plastic synapses. These roles reproduce the differential effects of PVs and SSTs in stimulus-specific adaptation, forward suppression and tuning-curve adaptation, as well as the influence of PVs on feedforward functional connectivity in the circuit. This circuit exhibits a balance of inhibitory and excitatory currents that persists on stimulation. This approach brings together multiple findings from different laboratories and identifies a circuit that can be used in future studies of upstream and downstream sensory processing.
We extend the theory of weakly coupled oscillators to incorporate slowly varying inputs and parameters. We employ a combination of regular perturbation and an adiabatic approximation to derive ...equations for the phase-difference between a pair of oscillators. We apply this to the simple Hopf oscillator and then to a biophysical model. The latter represents the behavior of a neuron that is subject to slow modulation of a muscarinic current such as would occur during transient attention through cholinergic activation. Our method extends and simplifies the recent work of Kurebayashi (
Physical Review Letters
,
111
, 214101,
2013
) to include coupling. We apply the method to an all-to-all network and show that there is a waxing and waning of synchrony of modulated neurons.
This paper presents an all-digital impulse radio ultra-wideband (IR-UWB) transmitter. All functional blocks in the transmitter are implemented with digital standard cells and automatically ...place-and-routed by design tools. The center frequency and the bandwidth of the UWB pulses are digitally tuned to compensate for variations, or target different applications. This paper also proposes a calibration scheme and modeling of a cell-based digitally controlled oscillator (DCO), which takes systematic mismatch from automatic place-and-route into account. The transmitter is fabricated in a 65 nm CMOS process, and occupies a core area of 0.032 mm 2 . The transmitter operates in the 3.1-5.0 GHz UWB band with leakage power of 170 μW and active energy consumption ranges from 8 pJ/pulse to 16 pJ/pulse, which combine to a total minimum energy/pulse of 12 pJ/pulse at 50 Mb/s.
The phytohormone abscisic acid (ABA) is crucial for plant growth and adaptive responses to various stress conditions. Plants continuously adjust the ABA level to meet physiological needs, but how ABA ...homeostasis occurs is not fully understood. This study provides evidence that UGT71B6, an ABA uridine diphosphate glucosyltransferase (UGT), and its two closely related homologs, UGT71B7 and UGT71B8, play crucial roles in ABA homeostasis and in adaptation to dehydration, osmotic stress, and high-salinity stresses in Arabidopsis (Arabidopsis thaliana). UGT RNA interference plants that had low levels of these three UGT transcripts displayed hypersensitivity to exogenous ABA and high-salt conditions during germination and exhibited a defect in plant growth. However, the ectopie expression of UGT71B6 in the atbgl (for β-glucosidase) mutant background aggravated the ABA-defìcient phenotype of atbgl mutant plants. In addition, modulation of the expression of the three UGTs affects the expression of CYP707A1 to CYP707A4, which encode ABA 8'-hydroxylases; four CYP707As were expressed at higher levels in the UGT RNA interference plants but at lower levels in the UGT71B6:GFP-overexpressing plants. Based on these data, this study proposes that UGT71B6 and its two homologs play a critical role in ABA homeostasis by converting active ABA to an inactive form (abscisic acid-glucose ester) depending on intrinsic cellular and environmental conditions in plants.
In recent times, with the increasing interest in conversational agents for smart homes, task-oriented dialog systems are being actively researched. However, most of these studies are focused on the ...individual modules of such a system, and there is an evident lack of research on a dialog framework that can integrate and manage the entire dialog system. Therefore, in this study, we propose a framework that enables the user to effectively develop an intelligent dialog system. The proposed framework ontologically expresses the knowledge required for the task-oriented dialog system's process and can build a dialog system by editing the dialog knowledge. In addition, the framework provides a module router that can indirectly run externally developed modules. Further, it enables a more intelligent conversation by providing a hierarchical argument structure (HAS) to manage the various argument representations included in natural language sentences. To verify the practicality of the framework, an experiment was conducted in which developers without any previous experience in developing a dialog system developed task-oriented dialog systems using the proposed framework. The experimental results show that even beginner dialog system developers can develop a high-level task-oriented dialog system.
The phytohormone abscisic acid (ABA) plays crucial roles in various physiological processes, including responses to abiotic stresses, in plants. Recently, multiple ABA transporters were identified. ...The loss-of-function and gain-of-function mutants of these transporters show altered ABA sensitivity and stomata regulation, highlighting the importance of ABA transporters in ABA-mediated processes. However, how the activity of these transporters is regulated remains elusive. Here, we show that spatial regulation of ATP BINDING CASETTE G25 (ABCG25), an ABA exporter, is an important mechanism controlling its activity. ABCG25, as a soluble green fluorescent protein (sGFP) fusion, was subject to posttranslational regulation via clathrin-dependent and adaptor protein complex-2-dependent endocytosis followed by trafficking to the vacuole. The levels of sGFP:ABCG25 at the plasma membrane (PM) were regulated by abiotic stresses and exogenously applied ABA; PM-localized sGFP:ABCG25 decreased under abiotic stress conditions via activation of endocytosis in an ABA-independent manner, but increased upon application of exogenous ABA via activation of recycling from early endosomes in an ABA-dependent manner. Based on these findings, we propose that the spatial regulation of ABCG25 is an important component of the mechanism by which plants fine-tune cellular ABA levels according to cellular and environmental conditions.
This work aims to predict the moisture evaporation in vegetable storage drawers of a household refrigerator with considering the operating conditions of a refrigerator and to propose a prediction ...model of moisture preservation for a long-term storage of vegetables. An experimental equipment was setup to evaluate the operating conditions, such as temperature and humidity control, cold airflow path, and structural design of a drawer. Moisture evaporation in fresh vegetables was evaluated quantitatively, and a new predictive model of moisture evaporation was developed on the basis of the data. The coefficient of determination was 93.2 % in the prediction model developed when spinach and bok choy were used in the basic experiment, which matched well with the experimental data obtained from a real refrigerator test with difference of approximately 0.4 %. We believe that the proposed approach can be utilized in the initial design stage of a vegetable drawer of a household refrigerator and is expected to be implemented in diverse applications related to fresh storage of vegetables.
In this paper, we propose a new natural language generation (NLG) method for spoken dialog systems and demonstrate its capacity. Studies on NLG often employ sequence decoding, which generates the ...words comprising a sentence in sequential order and uses the input generated by each word in the previous step. In contrast, we propose a decoding method that employs a sequence generated by traversing a dependency tree with feed input to a pair consisting of a parent and sibling in the dependency tree. As a result, the most important words are generated first, thereby enabling words with greater relevance to be fed into the process. At prediction time, our model generates dependency trees and converts the trees into sentences. The proposed decoding method was evaluated by re-implementing a semantically controlled long short-term memory structure for NLG, and the input and predicted sequence were converted to allow dependency tree decoding. The experimental results indicated that our suggested approach, i.e., dependency tree decoding, dramatically elevates the BLEU-score and naturalness. Furthermore, when creating sentences with <inline-formula> <tex-math notation="LaTeX">{n} </tex-math></inline-formula>-best using dependency tree decoding, the word diversity of the output sentences was increased by approximately 6%, offering a more diverse sentence pattern.