Artificial Intelligence Overview

What is AI in 5 Min?

Computer science => AI

Artificial Intelligence is a new revolution in the world by making intelligent machines. The Artificial Intelligence is now all around us. It is currently working with a variety of sub-fields, ranging from general to specific, such as self-driving cars, playing chess, proving theorems, playing music, Painting, etc. and various popular topics such as History of AI, applications of AI, deep learning, machine learning, natural language processing, Reinforcement learning, Q-learning, Intelligent agents, Various search algorithms, etc.
Artificial Intelligence is composed of two words Artificial and Intelligence, where Artificial defines "man-made," and intelligence defines "thinking power", hence AI means "a man-made thinking power.

Why artificial intelligence?

what is the importance of AI and why should we learn it? Following are some main reasons to learn about AI:

• AI can create such software or devices which can solve real-world problems very easily and with accuracy such as health issues, marketing, traffic issues, etc.
• AI can create your personal virtual Assistant, such as Cortana, Google Assistant, Siri, etc.
• AI can build such Robots which can work in an environment where survival of humans can be at risk.
• AI opens a path for other new technologies, new devices, and new Opportunities.

What are the Goals of Artificial Intelligence

Following are the main goals of Artificial Intelligence:

1. Replicate human intelligence
2. Solve Knowledge-intensive tasks
3. An intelligent connection of perception and action
4. Building a machine which can perform tasks that requires human intelligence such as:
• Proving a theorem
• Playing game
• Plan some surgical operation
• Self-Driving car in traffic
5. Creating some system which can exhibit intelligent behavior, learn new things by itself, demonstrate, explain, and can advise to its user.

What Comprises to Artificial Intelligence?

Artificial Intelligence is not just a part of computer science even it's so vast and requires lots of other factors which can contribute to it. To create the AI first we should know that how intelligence is composed, so the Intelligence is an intangible part of our brain which is a combination of Reasoning, learning, problem-solving perception, language understanding, etc.

To achieve the above factors for a machine or software Artificial Intelligence requires the following discipline:

• Mathematics
• Biology
• Psychology
• Sociology
• Computer Science
• Neurons Study
• Statistics

Pros and Cons of AI

Advantages of Artificial Intelligence

• High Accuracy with less errors
• High-Speed
• High reliability
• Useful for risky areas
• Digital Assistant
• Useful as a public utility

Disadvantages of Artificial Intelligence

• High Cost
• Can't think out of the box
• No feelings and emotions
• Increase dependency on machines
• No Original Creativity

AI Techniques

Speech Recognition:

Human can speak and listen communicate through language this is a field of speech recognition.

Statistical Learning:

Much of speech recognition is statistical based hence it is statistical learning.

Natural Language Processing (NLP):

Humans can read and write in a language hence it is called the field of natural language processing (NLP).

Computer Vision:

Humans can see with their eyes and process what they see this is the field of computer vision.

Symbolic Learning:

Computer vision falls under the symbolic way of learning for computers to process information.

Image Processing:

Humans recognize the scene around them through eyes which creates images of it and process which is called image processing even though it is not directly related to AI but it requires for computer vision.

Robotics:

Humans can understand their environment and they can act accordingly and can move fluidly this field is called robotics.

Pattern Recognition:

Humans have ability to see patterns such as grouping of like objects this is a field of pattern recognition.

Machine Learning:

Machines are even better at pattern recognition because they can use more data and dimensions of data. Machine Learning is making the computer learn from studying data and statistics. machine learning is a step into the direction of artificial intelligence (AI). machine learning is a program that analyses data and learns to predict the outcome.

Supervised Learning:

 If you train an algorithm with data that contains answer that is called supervised learning. In supervised learning, the output data-sets are provided which are used to train the machine and get the desired outputs.

Unsupervised Learning:

If you train an algorithm with data where you want the machine to figure out the patterns, then it is called unsupervised learning. For unsupervised learning no data-sets are provided, instead the data is clustered into different classes. The most common unsupervised learning method is cluster analysis, which is used for exploratory data analysis to find hidden patterns or grouping in data.

Reinforcement Learning:

If you give any algorithm a goal and expect the machine to achieve by trial and error, then it is called reinforcement learning. Reinforcement learning is a feedback-based learning method, in which a learning agent gets a reward for each right action and gets a penalty for each wrong action. The agent learns automatically with these feedback and improves its performance.

Deep Learning:

Deep learning is known as deep structured learning or hierarchical learning and is part of a broader family of machine learning methods based on learning data representations, as opposed to task-specific algorithms. Learning can be supervised, semi-supervised or unsupervised. When neural networks are more complex and deeper, and we use those to learn complex things that is the field of deep learning. There are different types of deep learning in machines which are essentially different technique to replicate what the human brain does.

Neural Networks:

The human brain is network of neuron and they use these to learn things if we can replicate the structure and function of the human brain, we might be able to get cognitive capability in machines this is the field of neural networks.

Convolution Neural Networks:

If we get the network to scan images from left to right and top to bottom its convolution neural networks.

Object Recognition:

It is used to recognize object in a scene.

Recurrent Neural Network:

Humans can remember past like what you were doing yesterday in the same way computers can be trained through neural networks it is called recurrent neural network.

Classification & Prediction

As you see there are two ways AI works one is symbolic based learning and other is data based called machine learning for data-based learning, we must feed the machine lots of data to learn. For example, if we have lots of data for sales and advertise spent you can plot that data to see pattern if the machine can learn this pattern it can make predication based on what it has learned. Unlike human machines can predict in multiple dimensions from lots of data. Once it learns these patterns it can make prediction that humans can’t even come close to you can use all these machine learning techniques to do one or two things classification or prediction.

Classification:

Classification are the absolute basics of machine learning generally its grouping technique,classification is called a supervised learning method.

Prediction:

 Prediction is action of forecast something in order to take decision and modify the action accordingly to get benefit out the action you have taken based on the prediction analytics.

Which computer language is used in artificial intelligence?

• AI programs have been written in just about every language ever created. The most common seem to be Lisp, Prolog, C/C++, recently Java, and even more recently, Python (knowledge of Python will be an advantage)
• Knowledge of essential Mathematics such as derivatives, probability theory, etc.