• 제어로봇시스템학회:학술대회논문집
• /
• 1992.10b
• /
• pp.324-329
• /
• 1992

A physical phenomenon is observed through analysis of the Hodgkin-Huxley's model that is, according to Maxwell field equations a fired neuron can yield magnetic fields. The magnetic signals are an output of the neuron as some type of information, which may be supposed to be the conscious control information. Therefore, study on neural networks should take the field effect into consideration. Accordingly, a study on the behavior of a unit neuron in the field is made and a new neuron model is proposed. A mathematical Memory-Learning Relation has been derived from these new neuron equations, some concepts of memory and learning are introduced. Two learning theorems are put forward, and the control mechanisms of memory are also discussed. Finally, a theory, i.e. Neural Electromagnetic(NEM) field theory is advanced.

• Journal of Digital Contents Society
• /
• v.18 no.6
• /
• pp.1165-1173
• /
• 2017

Deep learning method, which is one of the most famous machine learning algorithms, has proven its applicability in various applications and is widely used in digital signal processing. However, it is difficult to apply deep learning technology to IoT devices with limited CPU performance and memory capacity, because a large number of training samples requires a lot of memory and computation time. In particular, if the Arduino with a very small memory capacity of 2K to 8K, is used, there are many limitations in implementing the algorithm. In this paper, we propose a method to optimize the ELM algorithm, which is proved to be accurate and efficient in various fields, on Arduino board. Experiments have shown that multi-class learning is possible up to 15-dimensional data on Arduino UNO with memory capacity of 2KB and possible up to 42-dimensional data on Arduino MEGA with memory capacity of 8KB. To evaluate the experiment, we proved the effectiveness of the proposed algorithm using the data sets generated using gaussian mixture modeling and the public UCI data sets.

• Journal of Institute of Control, Robotics and Systems
• /
• v.9 no.7
• /
• pp.527-535
• /
• 2003

A behavior-based control and learning architecture is proposed, where reinforcement learning is applied to learn proper associations between stimulus and response by using two types of memory called as short Term Memory and Long Term Memory. In particular, to solve delayed-reward problem, a knowledge-propagation (KP) method is proposed, where well-designed or well-trained S-R(stimulus-response) associations for low-level sensors are utilized to learn new S-R associations for high-level sensors, in case that those S-R associations require the same objective such as obstacle avoidance. To show the validity of our proposed KP method, comparative experiments are performed for the cases that (ⅰ) only a delayed reward is used, (ⅱ) some of S-R pairs are preprogrammed, (ⅲ) immediate reward is possible, and (ⅳ) the proposed KP method is applied.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.409-410
• /
• 2022

This paper proposes a fusion model based on Long-Short Term Memory networks (LSTM) and CNN deep learning methods, and applied to multi-category news datasets, and achieved good results. Experiments show that the fusion model based on deep learning has greatly improved the precision and accuracy of text sentiment classification. This method will become an important way to optimize the model and improve the performance of the model.

• KIPS Transactions on Software and Data Engineering
• /
• v.7 no.8
• /
• pp.307-324
• /
• 2018

Recently, recurrent neural networks have been attracting attention in solving prediction problem of sequential data through structure considering time dependency. However, as the time step of sequential data increases, the problem of the gradient vanishing is occurred. Long short-term memory models have been proposed to solve this problem, but there is a limit to storing a lot of data and preserving it for a long time. Therefore, research on memory-augmented neural network (MANN), which is a learning model using recurrent neural networks and memory elements, has been actively conducted. In this paper, we describe the structure and characteristics of MANN models that emerged as a hot topic in deep learning field and present the latest techniques and future research that utilize MANN.

• Korean Journal of Cognitive Science
• /
• v.7 no.3
• /
• pp.7-36
• /
• 1996

Recebt neuropsychological studies on neurobiological bases of learning and memory in humans are reviewed. At present, cognitive psychologists belive that memory is not a unitary system. But copmosed of several independent subsystems. Adoption this perspective,this paper summarized findings regarding what kinds of memory discorders result from lesions of which brain areas and which brain areas are activated by what kind of learning/memory tasks. Short-term memory seems to involve widespread areas around the boundaries among the parietal,occipital,and temporal lobes,depending on the type of the type of the tasks and the way of presentation of the stimuli. Implicit memory,a subsystem of long-term memory,is not a unitary system itself. Thus,brain areas involved in implicit memory tasks used. It is well-known that medial temporal lobe is necessary for formation(i,e.,consolidation)of explicit memory,another subsystem of long-term memory. Storage and/or retrieval of episodic and semantic memory involve temporal neocortex. Perfromtal cortex seemas to be involved in several aspects of memory such as short term memory and retrieval of espisodic and semantic memory. Finally, a popular view on the locus of long-term memory storage is described.

• International Journal of Computer Science & Network Security
• /
• v.21 no.11
• /
• pp.23-30
• /
• 2021

Sentiment Analysis has become very important field of research because posting of reviews is becoming a trend. Supervised, unsupervised and semi supervised machine learning methods done lot of work to mine this data. Feature engineering is complex and technical part of machine learning. Deep learning is a new trend, where this laborious work can be done automatically. Many researchers have done many works on Deep learning Convolutional Neural Network (CNN) and Long Shor Term Memory (LSTM) Neural Network. These requires high processing speed and memory. Here author suggested two models simple & bidirectional deep leaning, which can work on text data with normal processing speed. At end both models are compared and found bidirectional model is best, because simple model achieve 50% accuracy and bidirectional deep learning model achieve 99% accuracy on trained data while 78% accuracy on test data. But this is based on 10-epochs and 40-batch size. This accuracy can also be increased by making different attempts on epochs and batch size.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.174-174
• /
• 2000

Q-learning, based on discrete state and action space, is a most widely used reinforcement Learning. However, this requires a lot of memory and much time for learning all actions of each state when it is applied to a real mobile robot navigation using continuous state and action space Region-based Q-learning is a reinforcement learning method that estimates action values of real state by using triangular-type action distribution model and relationship with its neighboring state which was defined and learned before. This paper proposes a new Region-based Q-learning which uses a reward assigned only when the agent reached the target, and get out of the Local optimal path with adjustment of random action rate. If this is applied to mobile robot navigation, less memory can be used and robot can move smoothly, and optimal solution can be learned fast. To show the validity of our method, computer simulations are illusrated.

• Journal of Oriental Neuropsychiatry
• /
• v.10 no.2
• /
• pp.105-113
• /
• 1999

The purpose of this study was to investigate the effect of Sunhyangjungkisan on the learning and memory ability in rats. For this purpose we have evoked cerebral dysfunction in rats with NOS inhibitor and then performed the Morris water maze task for each rat. We have found that Sunghyangjungkisan have some improving effedts on impaired learning and memort ability in the NOS inhibitor treated rat. In these improving effects, memory effect was more evident then learning effect. This result implies that Sunghyangjungkisan may be one of useful prescriptions for treatment of vascular dementia after cerebral ischemia.

• Journal of Oriental Neuropsychiatry
• /
• v.8 no.1
• /
• pp.69-79
• /
• 1997

This study was conducted to find out the effects of Jowiseungchungtang on learning and memory of rats. For this purpose, the radial-arm maze was used. The results of the study were summarized as follows.1. It was shown that the rate of rats that met the learning criteria when performing the learning is that the control group amounted to 40.0% while the Jowiseungchungtang group did 73.3%. The other showed higher learning effect than the one but there was no statistical significance.2. In the retention test performed with rats that met the learning criteria, the frequency of errors made by the two groups was 3.33$\pm$2.25 times for the control group and 1.36$\pm$1.12 times for Jowisrungchungtang group. The other was remarkably lower than the one in the frequency of errors.In conclusion, the study suggested that the Jowiseungchungtang have an effect on improvement of learning and memory.