Advances in technology will continue to reach far into every sector of our economy. Future job and economic growth in the industry, defence, transportation, agriculture, healthcare, and life sciences are directly related to scientific advancement,” said Christopher “Kit” Bond, a former U.S. Senator.
Indeed, technology becomes an integral aspect of this generation, whether in business, work or personal life. Billions of people today (perhaps including yourself) use social media, search, and virtual assistant applications almost every day. Have you ever wondered how Siri or Alexa works? Or how Facebook recognizes pictures of you and your friends? It is normal to be baffled on how these technologies work. Let’s dive in to learn more on how that stuff works—welcome the age of AI powered by Artificial Neural Network.
The Artificial Neural Network(ANN) and How It Works
Artificial Neural Network
Psychologist Frank Rosenblatt invented the first Artificial Neural Network or ANN called “Perceptron” in 1958. It was designed to imitate the way a human brain processes and analyzes visual data, like pictures and words. Also, it helps computers, devices, and software to have a self-learning ability and enables them to recognize objects, analyze patterns, and even solve problems that are impossible or too difficult for human standards.
(Photo source: “Google’s AI: From DeepMind to One Model,” Stanford University)
Google DeepMind is one of the best examples of an advanced neural network that drives the future of machine learning. Google DeepMind made an AI system called AlphaGo that plays the Chinese board game Go. By learning through an artificial neural network, AlphaGo has beaten the professional Go player and 18-time world champion, Lee Sedol, with a brutal score of 4-1 last 2016. It created a buzz in the tech world.
(Photo source: “Blue-Collar Revenge: The Rise of AI Will Create A New Professional Class,” Forbes)
ANN can learn from its “experiences” or based on previous data and patterns it has processed. Thus, AlphaGo was able to beat the grandmaster using its brilliant “artificial neurons.”. In more recent news Google DeepMind has announced shifting its AI focus from games to science: “From building “AI agents” that can play games to building AI agents that can have real world impact, particularly in areas of science like biology.”. Google DeepMind is planning on using its AI products and research to leverage advances in healthcare, physics and global warming.
Neurons and Synapses
Synthetic synapses connect artificial neurons. Synapses serve as a connector that allows the transfer of information or signal from one neuron to another. ANN’s neurons and synapses can perform calculations and create neuromorphic chips to understand images, sounds and respond to changes in data.
These hundreds or thousands of artificial neurons that are connected by the synapses, process information through the three distinct layers; 1) input layer, 2) hidden layer, and 3) output layer. They work together to produce and present one output report.
The Three Layers(Image from Scientific American, Unveiling the Hidden Layers of Deep Learning)
-The function of the Input Layer is to deal with all the input information and pass the encoded and numerical data to the Hidden Layer.
-A hidden layer consists of multiple layers that filter patterns and apply a different transformation to the input data to something the Output Layer can use.
–Output Layer of the ANN, which receives and collects data from the previous layer and transmits the given designed data.
- Input layers are like researchers, they gather, analyze and interpret all the needed raw data for a research study.
- Hidden layers are like vintner, they extract substances from quality grapes and use them to create the best, wine out of it.
- Output Layer is like corporate secretaries, they sometimes receive messages and instructions from different callers, e.g., clients, employees, and people in business and inform his/her bosses about them.
Learning How the Neural Networks Learn
As mentioned earlier, ANN can work the way the human brain works and can learn the way we learn. Howard Rheingold, an American critic, teacher, and writer who’s famous for his specialties on the social, cultural and political implications of modern technology, stated;
“The neural network is this kind of technology that is not an algorithm, it is a network that has weights on it, and you can adjust the weights so that it learns. You teach it through trials.”
It’s a fact that the neural network can operate and improve its performance after “teaching” it but it needs to undergo some process of learning to acquire information and be familiar with them.
ANN’s Method of Learning
ANN can also learn through different methods and techniques. Here are ANN’s three methods of learning.
This method of learning is dependent because it’s under the supervision of facilitators called data scientists. With the help of this process, it can categorize unlabeled data into two groups: Classification and Regression. Deep Learning–Computer Vision and Convolutional Neural Networks Posted by ANH VO on FEBRUARY 1
- Classification is a method of prediction or identification which class the input data is part of(discrete value). For example, the computer analyzes and pictures if it’s an animal or not—like solving a yes or no problem—then categorize by its kind, whether it’s a dog or a cat.
- Regression is an estimation process between two variables and their relationship. This method analyzes or predicts the value of the input based on the given data. Let’s say, a product’s data is already available—the size, weight, height or anything—regression then predicts the price or the value of the product.
As a human, we can improve better with a teacher, so does ANN; it can learn by example. Data scientists teach ANN algorithms by providing correct answers or possible programming conclusions.
In unsupervised learning, the system is provided or presented with unlabeled input data, and the system’s algorithms act independently and group the uncategorized information based on similarities and differences without being supplied with the correct outputs.
Here are two methods of unsupervised learning:
Cluster Analysis is a tool to solve classification problems; it sorts or sub-divide things, people, events, etc., into groups, or clusters, according to their similarity, to strengthen the degree of association and connection between members of the same cluster. It’s objective is to reveal relationships, structures, association and hidden patterns in mass data.
Associate Analysis is a discovery method to reveal relationships among variables in huge data, and how those data are related to or associated with each other—making an easier way to come up with outputs. Like when we buy an item on Amazon, there re suggestion such as: “Customers also bought,” and giving similar items that we purchased. Moreover, all these suggestions are based on the past information that is related to the presented data.
This method allows machines to automatically determine the best behavior or action depending on the circumstance, to maximize or improve its performance. Reward feedback is needed for machines to learn; this is called the reinforcement signal. This method allows the artificial neural network not just to function as the brain, but also to behave and act like the biological one.
- Supervised Learning: you teach a child what people’s gender is by showing examples or photos who’s a girl and who’s a boy.
- Unsupervised Learning: you ask a child to group people based on gender.
- Reinforcement Learning: you show a child you hug people if they are girls and shake their hands if they are boys.
Smarter Future of Neural Networks
Since the invention of computers, others doubted its capacity to be useful, but some also expected and hoped that its something that would help humanity in the future. And they were right; codes to create an artificial brain were developed, machines used to do just what they are programmed to do, but now they can even act and learn independently. The more information machines and computers successfully process, the smarter they become.
Albert Einstein once shared his opinion regarding the future of technology, he said; “I fear the day that technology will surpass our human interaction. The world will have a generation of idiots.” It’s incredible that ANN is taking technology to the next level, and it’s something to be excited about; however, we should utilize it properly. It serves as a challenge at the same time a great deal of responsibility among scientists and developers, to maintain the balance between humanity and artificial intelligence, and to make sure that AI would not cross the line.
Nowadays, the age of smart devices dominates the technological world, and no one can deny their great value and contributions to mankind. Their intelligence is becoming more human-like, thanks to the continuous AI research and studies of software engineers, programmers, and data scientists. As a result, there’s a massive demand for skilled developers and engineers from prominent and start-up companies. If you want to take part in this Fourth Industrial Revolution, the first significant step you should take is to learn how to code. Codes are the core of AI because it makes up ANN. Whether you have a coding background or a little to no experience, Coding Dojo can help you become a developer and learn multi stacks/frameworks within 14 weeks! If you’re interested, visit codingdojo.com for more info!