Artificial Intelligence: What is it in reality ?
Artificial intelligence (AI) uses machine learning models for predictions. Goals of AI include learning, perception and reasoning.
Artificial intelligence (AI) is the simulation of human actions and intelligence by computers. It is a combination of many technologies such as Machine Learning, Natural Language Processing and Applied Intelligence.
Characteristics of AI:
- Rationalize tasks for a specific goal
- Categorization
- Classification & Collaborative filtering
Types of Artificial Intelligence:
Based on the capabilities and usability, AI is classified into different categories:
Reactive machines
Reactive machines don’t have the ability to learn and adapt, hence they are not used for memory based scenarios and can be used for automatic responses to a limited set of inputs.
Use cases: Chat bots for customer service and engagement
Limited memory
Limited memory machines are capable of learning from historical data and make decisions.
Most of the AI machines today fall under this category. They use deep learning techniques for training and storing memory for these machines.
Use cases: Driverless cars, Image recognition, Virtual assistants
Theory of mind
This type of AI is still under research and development.
Theory of mind is designed to truly understand human needs and react based on emotions and thought process.
Self aware
This type of AI is hypothetical at the moment. Self aware AI will have the capabilities of a human brain through which it can develop self awareness.
We can classify Self Aware AI into two categories:
a. Artificial Narrow Intelligence (ANI):AI machines that can perform a specific task like humans in which they are trained. Hence, they have very narrow capabilities.
b. Artificial General Intelligence (AGI): AI machines that can learn and understand tasks on their own. They have the capability of building their own competencies and form a network of connections across domains, saving a lot of training time/effort.
c. Emotional Intelligence (EI): EI is a combination of AI and emotions, it is the capacity of recognizing emotions and guide thought process and tasks.
Integrating AI & EI can benefit functional teams such as tech, sales and customer service. A mobile app/chat bot detects the emotional quotient of a customer and respond with recommendations.
Use cases: Personalized learning, Customer service
Deep learning:
Deep learning is a machine learning technique that teaches systems to learn by example.
All present day AI systems are based on deep learning, they are trained by large volumes of data that they store in their memory to form a reference model for solving problems.
Use cases: Voice control in consumer devices, Driverless cars
How does it work ?
In deep learning, a model learns to perform classification tasks directly from images, text, video or audio.
Models are trained by using a large set of labeled data and neural network architectures that contain many layers.
Labeled data is the set of data that is tagged for the system to recognize.
Example: A voice control assistant on a consumer device will be trained with sound/text/videos of different settings and features of the device to perform tasks dictated by the user.
A Neural Network is an adaptive system that learns by using interconnected nodes in a layered structure. A neural network can learn from data and can be trained to recognize patterns, forecast events and classify data. Convolutional Neural Network (CNN), is the most popular neural network.
To conclude, in this blog post we have learnt about different types of AI and key components which AI systems are built on. In the next blog, I will elaborate more on deep learning concepts that are key for building AI systems.
I hope you enjoyed reading this article and you know the drill — clap, comment and share. Cheers, Karthik
