• KIPS Transactions on Computer and Communication Systems
• /
• v.7 no.4
• /
• pp.99-102
• /
• 2018

Caffe is a neural net learning software which is widely used in academic researches. The GPU memory capacity is one of the most important aspects of designing neural net architectures. For example, many object detection systems require to use less than 12GB to fit a single GPU. In this paper, we extended Caffe to allow to use more than 12GB GPU memory. To verify the effectiveness of the extended software, we executed some training experiments to determine the learning efficiency of the object detection neural net software using a PC with three GPUs.

• The Korea Journal of Herbology
• /
• v.30 no.1
• /
• pp.67-75
• /
• 2015

Objectives : The aim of this study is to examine the neuroprotective effect of wheat bran extract (WBE) against ${\beta}$-amyloid ($A{\beta}$)-induced apoptotic cell death in SH-SY5Y human neuroblastoma cells and memory impairment in triple transgenic animal model's of Alzheimer's disease (3xTg AD mice). Methods : In SH-SY5Y cells, MTT assay and TUNEL staining were conducted to evaluate the protective effect of WBE against $A{\beta}_{25-35}$-induced neurotoxicity and apoptosis. Alterations in mitochondrial transmembrane potential (MMP), expression of proapoptotic Bax and antiapoptotic Bcl-2 proteins, cleavage of PARP, and brain-derived neurotrophic factor (BDNF) levels were analyzed to elucidate the neuroprotective mechanism of WBE. To further investigate the memory enhancing effect of WBE, Morris water maze test was performed in 3xTg AD mice. Results : In SH-SY5Y cells, WBE protected against $A{\beta}_{25-35}$-caused cytotoxicity and apoptosis as shown by the restoration of cell viability in MTT assay and inhibition of DNA fragmentation in TUNEL staining. $A{\beta}_{25-35}$-induced apoptotic signals such as dissipation of MMP, decreased Bcl-2/Bax ratio, and cleavage of PARP were suppressed by WBE. Moreover, WBE up-regulated the protein levels of BDNF, which seemed to be mediated by activation of cAMP response element-binding protein (CREB). In 3xTg AD mice, oral administration of WBE attenuated learning and memory deficit as verified by reduced mean escape latency in water maze test. Conclusions : WBE protects neuronal cells from $A{\beta}_{25-35}$-induced apoptotic cell death and restores learning and memory impairments in 3xTg AD mice. These findings suggest that WBE exhibit neuroprotective potential for the management of AD.

• Journal of IKEEE
• /
• v.23 no.1
• /
• pp.120-126
• /
• 2019

Recently, accurate prediction of power consumption based on machine learning techniques in Internet of Energy (IoE) has been actively studied using the large amount of electricity data acquired from advanced metering infrastructure (AMI). In this paper, we propose a deep learning model based on Gated Recurrent Unit (GRU) as an artificial intelligence (AI) network that can effectively perform pattern recognition of time series data such as the power consumption, and analyze performance of the prediction based on real household power usage data. In the performance analysis, performance comparison between the proposed GRU-based learning model and the conventional learning model of Long Short Term Memory (LSTM) is described. In the simulation results, mean squared error (MSE), mean absolute error (MAE), forecast skill score, normalized root mean square error (RMSE), and normalized mean bias error (NMBE) are used as performance evaluation indexes, and we confirm that the performance of the prediction of the proposed GRU-based learning model is greatly improved.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.31B no.9
• /
• pp.159-165
• /
• 1994

In this paper, we propose a multi-layer associative neural network structure suitable for hardware implementaion with the function of performance refinement and improved robutst capability. Unlike other methods which reduce network complexity by putting restrictions on synaptic weithts, we are imposing a requirement of hidden layer neurons for the function. The proposed network has synaptic weights obtainted by Hebbian rule between adjacent layer's memory patterns such as Kosko's BAM. This network can be extended to arbitary multi-layer network trainable with Genetic algorithm for getting hidden layer memory patterns starting with initial random binary patterns. Learning is done to minimize newly defined network error. The newly defined error is composed of the errors at input, hidden, and output layers. After learning, we have bidirectional recall process for performance improvement of the network with one-shot recall. Experimental results carried out on pattern recognition problems demonstrate its performace according to the parameter which represets relative significance of the hidden layer error over the sum of input and output layer errors, show that the proposed model has much better performance than that of Kosko's bidirectional associative memory (BAM), and show the performance increment due to the bidirectionality in recall process.

• Proceedings of the KIEE Conference
• /
• 1989.11a
• /
• pp.488-493
• /
• 1989

In this paper, the structure of CMAC address mapping is first revisited, and the address hashing function and the random mapping is discussed in the conventional CMAC implementation. Then the effective size of CMAC memory is derived from the modulus property of the CMAC address vector, and a new hashing function for the effective memory mapping is proposed for a CMAC implementation with feasible memory size and no troublesome random mapping. Finally, the performance of the conventional CMAC learning algorithm and that of the proposed new CMAC scheme arc compared via simulations.

• Journal of Information Technology Applications and Management
• /
• v.31 no.1
• /
• pp.177-188
• /
• 2024

In this research, a cohort of two children, aged 7-8 years, was selected to participate in a specialized three-week training program aimed at enhancing their working memory. The program consisted of three sessions, each lasting approximately 30 minutes. The primary goal was to investigate the impact and developmental trajectory of working memory in school-aged children. Working memory plays a significant role in young children's learning and daily activities. To address the needs of this demographic, products should offer both educational and enjoyable activities that engage working memory. Digital educational tools, known for their flexibility, are suitable for both older individuals and young children. By updating software or modifying content, these tools can be effectively repurposed for young learners without extensive hardware changes, making them both cost-effective and practical. For example, memory training games initially designed for older adults can be adapted for young children by altering images, music, or storylines. Furthermore, incorporating elements familiar to children, like animals, toys, or fairy tales, can increase their engagement in these activities. Historically, working memory capabilities have been assessed predominantly through traditional intelligence tests. However, recent research questions the adequacy of these behavioral measures in accurately detecting changes in working memory. To bridge this gap, the current study utilized electroencephalography (EEG) as a more sophisticated and precise tool for monitoring potential changes in working memory after the training. The research findings were revealing. Participants showed marked improvement in their performance on n-back tasks, a standard measure for evaluating working memory. This improvement post-training strongly supports the effectiveness of the training program. The results indicate that such targeted and structured training programs can significantly enhance the working memory abilities of children in this age group, providing promising implications for educational strategies and cognitive development interventions.

• Archives of Pharmacal Research
• /
• v.28 no.6
• /
• pp.691-698
• /
• 2005

Phlorotannins, the polyphonic compounds found in brown Eisenia and Ecklonia algae, have several pharmacologically beneficial effects such as anti-inflammation. In addition, our recent data show that these compounds may improve the cognitive functions of aged humans suggesting the potential ability to enhance memory in several neurodegenerative disorders. To examine the experimental hypothesis that two effective components of Ecklonia cava, dieckol and phlorofucofuroeckol (PFF), have memory-enhancing abilities, both were administered orally to mice before a passive avoidance test. The repeated administration of either dieckol or PFF dose-dependently reduced the inhibition of latency by the administration of ethanol. To investigate the mode of memory-enhancing actions, the levels of major central neurotransmitters in three different regions (striatum, hippocampus, and frontal cortex) of the mouse brain were measured. The levels of some of the neurotransmitters were significantly changed by ethanol. Both dieckol and PFF altered the levels of some neurotransmitters modified by the ethanol treatment. It is noteworthy that both dieckol and PFF increased the level of acetylcho-line, and they exerted anticholinesterase activities. Overall, the memory-enhancing abilities of dieckol and PFF may result from, at least in part, the increment of the brain level of acetylcho-line by inhibiting acetylcholinesterase.

• 제어로봇시스템학회:학술대회논문집
• /
• 1989.10a
• /
• pp.653-662
• /
• 1989

Cerebellar Model Arithmetic Controller (CMAC) has been introduced as an adaptive control function generator. CMAC computes control functions referring to a distributed memory table storing functional values rather than by solving equations analytically or numerically. CMAC has a unique mapping structure as a coarse coding and supervisory delta-rule learning property. In this paper, learning aspects and a convergence of the CMAC were investigated. The efficient training algorithms were developed to overcome the limitations caused by the conventional maximum error correction training and to eliminate the accumulated learning error caused by a sequential node training. A nonlinear function generator and a motion generator for a two d.o.f. manipulator were simulated. The efficiency of the various learning algorithms was demonstrated through the cpu time used and the convergence of the rms and maximum errors accumulated during a learning process. A generalization property and a learning effect due to the various gains were simulated. A uniform quantizing method was applied to cope with various ranges of input variables efficiently.

• Journal of Fisheries and Marine Sciences Education
• /
• v.16 no.2
• /
• pp.163-170
• /
• 2004

The rapid exchanges of mobile computing environment and development of wireless communication are providing many effects for learning activity of students. Recently, PDA system developers which are studying memory capacity, communication speed and size of screen support techniques to be capable of learning from students in the wireless or moving environment. In this viewpoints, this paper has a purpose to design multimedia learning system to be able to do with sound lecture contents. The implemented system largely consists of two parts which have the teacher module and students module. The one manages learning progress of students, class management, bulletin board and etc. The other is capable of using studying and bulletin functions. The main idea of this research is focus to upgrade the effect of learning without almost treating the existing studies, which can be listening sound lecture and also seeing text and image at the same time.

• BMB Reports
• /
• v.42 no.5
• /
• pp.239-244
• /
• 2009

New neurons are continually generated in the subgranular zone of the dentate gyrus and in the subventricular zone of the lateral ventricles of the adult brain. These neurons proliferate, differentiate, and become integrated into neuronal circuits, but how they are involved in brain function remains unknown. A deficit of adult hippocampal neurogenesis leads to defective spatial learning and memory, and the hippocampi in neuropsychiatric diseases show altered neurogenic patterns. Adult hippocampal neurogenesis is not only affected by external stimuli but also regulated by internal growth factors including BDNF, VEGF and IGF-1. These factors are implicated in a broad spectrum of pathophysiological changes in the human brain. Elucidation of the roles of such neurotropic factors should provide insight into how adult hippocampal neurogenesis is related to psychiatric disease and synaptic plasticity.