Skip main navigation

Artificial Neural Networks and Applications

TBC
14.5
Hello everybody. Today I want to introduce Artificial Neural Networks and their applications. This is an outline of today’s course including Introduction, Fundamental Concept of Artificial Neural Networks, Brief Introduction of Deep Learning, Applications. Now I’m going to start with introduction. Please remind that what do Fuzzy sets and fuzzy logic do? The answer is Fuzzy sets and fuzzy logic imitate the way the brain deals with inexact information. In contrast, artificial neural networks are modeled to imitate the physical architecture of the brain. Artificial neural networks have the ability to classify, store, recall and associate information or patterns. I will say that artificial neural networks have the learning ability. Now I am going to introduce the Fundamental Concept of Artificial Neural Networks.
105.3
Before mentioning about the artificial neural networks, we have to see what is neuron. The figure on the left is the real neuron. The dendrite can receive the electrochemical stimulation from other neural cells. The cell body can do some process for the stimulation and transmit it to different neurons through Axon. The figure on the right is the artificial neuron. Here the x is the input and the w is the weight for the input. The weighted inputs are processed by the processing element to get the output y. You can see that the artificial neuron works just like the real one. By different kinds of connection of artificial neurons, we can obtain different kinds of artificial neural networks.
184.6
Every neural networks has its own learning rule. The learning rules can be categorized into three major types, Supervised Learning, Unsupervised Learning and Reinforcement Learning For supervised learning, we have to teach the artificial neural network what is the correct answer. Unsupervised learning is like that children will cluster similar things without our teaching. Reinforcement learning is to teach the artificial neural network for taking action to get maximum reward. Now Let’s go a little deeper in artificial neural networks that is deep learning. We can see here Deep learning is a subset of AI. Deep learning is implemented by deep neural networks which are more complicated multi-layer neural networks. Recently, the dramatic increase in computer power makes the deep learning possible.
267.1
We can say that the deep learning has brought us to a new generation of AI. I think the ALPHOGO is one of the most representative applications of deep learning. It was considered to be almost impossible that a computer program could beat the GO world champion before the birth of ALPHOGO. We can see here the ALPHOGO applies a deep neural network. Finally we can see some applications of Artificial Neural Networks Artificial neural net works can be applied for AI to play video games. It can also be use for Object Detection. The artificial neural networks YOLO can detect objects in real time. It’s a difficult task for robot to fetch objects of random shapes.
337.3
Artificial neural networks can be applied to detect Robotic Grasps for fetching them. Moreover, Artificial neural net works can be applied for decision making, recognition, etc.

In this video, Prof. Cheng will introduce Artificial Neural Networks. He will start with the fundamental concept of Artificial Neural Networks, brief Introduction of deep learning, and applications.

Prof. Cheng will first introduce the Artificial neural network (ANN). ANN is a computational model that consists of several processing elements that receive inputs and deliver outputs based on their predefined activation functions. ANN can be part of deep learning models. Deep learning is implemented by deep neural networks which are more complicated multi-layer neural networks. ALPHOGO is one of the most representative applications of deep learning.

Then, he will give some examples of Applications of Artificial Neural Networks applications. Artificial neural networks can be applied for AI to play video games. It can also be used for object detection. For example, Artificial neural networks YOLO can detect objects in real-time. It’s actually a difficult task for a robot to fetch objects of random shapes. Thus, Artificial neural networks can be applied for much more complicated tasks even in decision making, recognition, etc. These developments has great potential in applying in different fields.

This article is from the free online

Applications of AI Technology

Created by
FutureLearn - Learning For Life

Reach your personal and professional goals

Unlock access to hundreds of expert online courses and degrees from top universities and educators to gain accredited qualifications and professional CV-building certificates.

Join over 18 million learners to launch, switch or build upon your career, all at your own pace, across a wide range of topic areas.

Start Learning now