The recent progress in Artificial Intelligence has been immense and exponential. The technology is making its way out of research labs and into our everyday lives, promising to help us tackle humanity’s greatest challenges.
Artificial intelligence and machine learning are very closely related and connected. Because of this relationship, your are actually looking into interconnection while investigating AI vs. machine learning.
What is artificial intelligence (AI)?
Artificial intelligence is the capability of a computer system to mimic human cognitive functions such as learning and problem-solving. Through AI, a computer system uses mathematics and logic to simulate people’s reasoning to learn from new information and make decisions.
What is Machine Learning (ML)?
Machine learning is an application of AI. It is the process of using mathematical models to help a computer learn without direct instruction. With the self-learn automation process in place, the computer system (machine) can continue learning and improving on its own, based on experience.
What is Deep Learning (DL)?
Deep learning is a system that thinks and learns like humans using artificial neural networks. It is a subset of ML, and the performance improves with more data.
Even though AI and machine learning are very closely connected, they are not the same. Machine learning is a subset of AI, which is broadly defined as the capability of a machine to imitate intelligent human behavior. Artificial intelligence systems are used to perform complex tasks in a way that is similar to how humans solve problems. How does it connect? Well, an “intelligent” computer uses AI to think like a human and perform tasks on its own. Machine learning is how a computer system develops its intelligence.
One way to train a computer to mimic human reasoning is to use a neural network, which is a series of algorithms that are modeled after the human brain. The neural network helps the computer system achieve AI through deep learning. This close connection is why the idea of AI vs. machine learning is really about the ways that AI and machine learning work together.
Example of AI with ML and DL
Source: Simple Learn
Types of AI
Reactivate Machines refer to the systems that only react. It does not form memories and does not use any past experiences for a new decision.
Limited Memory is the system that investigates the past. Information is added over a period of time and is short-lived.
Theory of Mind is where the systems can understand human emotions and how they affect decision making. “They” adjust their behaviors according to their “human” understanding.
Self-Awareness is where the systems being aware of themselves and understand their own internal states and have capabilities of predicting other people’s feeling and act appropriately.
Types of ML
Supervised Learning can predict future outcomes based on past data. It requires both an input and an output to be given to the model for it to be trained.
Unsupervised Learning can identify hidden patterns from input data provided by making the data more readable and organized, the patterns, similarities or anomalies become more evident.
Types of DL
Deep Learning networks are the mathematical models that are used to mimic the human brains as it is meant to solve problems using unstructured data. These mathematical models are created in form of neural network that consists of neurons.
Feedforward neural network is the basic neural network where the flow control occurs from the input layer and goes towards the output layer. It has single layers or only one hidden layer. This DL is used in the facial recognition algorithm using computer vision.
Radial basis function neural networks generally have more than one layer preferably two layers. The relative distance from any point to the center is calculated, and the same process repeats in the next layer. This type of DL is generally used in power restoration systems to restore the power in the shortest period to avoid blackouts.
Multi-layer perceptron is where the network has more than three layers, and it is used to classify the data which is not linear. These networks are fully connected with every node and extensively used for speech recognition and other machine learning technologies.
Convolution neural network (CNN) is one of the variations of the multilayer perceptron. CNN can contain more than one convolution layer and since it contains a convolution layer, the network is very deep with fewer parameters. CNN is very effective for image recognition and identifying different image patterns.
Recurrent neural network (RNN) is a type of neural network where the output of a particular neuron is fed back as an input to the same node. This method helps the network to predict the output. This kind of network is useful in maintaining a small state of memory which is very useful for developing the chatbot. This kind of network is used in chatbot development and text-to-speech technologies.
Modular neural network is a combination of multiple small neural networks. All the sub-networks make a big neural network and all work independently to achieve a common target. It helps in break the small-large problem into small pieces and then solving it.
Sequence to sequence models is a combination of two RNN networks. It works on encoding and decoding; it consists of the encoder used to process the input and a decoder that processes the output. Generally, this kind of network is used for text processing where the length of the input text is not as same as output text.
References: