Introduction to artificial intelligence, machine learning, and deep learning.
Today, in the changing pace of development in the world, there is a great significance to the word “artificial intelligence” but sometimes we get confused between the terms artificial intelligence, machine learning and deep learning. So today, let us resolve a great conflict between these terms.
Learning for today
1. What is Artificial Intelligence?
2. What is Machine Learning?
3. What is Deep Learning?
What is Artificial Intelligence?
The art of machines that perform functions that require intelligence performed by people.
-Kurzweil, 1990
The branch of computer science that is concerned with automation of intel behavior.
-Luger and Stubblefield, 1993
By these two definitions, it is clear that with artificial intelligence, we are focusing on the machines and trying to make them smart.
Types of AI
There are two types of AI and it purely depends on the usage of which type is associated with that task.
Type I
1. Narrow AI
It is a type of artificial intelligence that is able to perform a dedicated task with intelligence. The most common and currently available artificial intelligence is narrow AI in the world of artificial intelligence. It cannot perform beyond its field or limitations, as it is only trained for one specific task.
2. General AI
It is a type of intelligence that could perform any intellectual task with efficiency, like a human. The idea behind general AI is to make systems that could be smarter and think like human by on their own.
3. Super AI
It is a level of intelligence in systems at which machines could surpass human intelligence and perform any task better than humans with cognitive properties. It is an outcome of general AI. Some key characteristics of strong AI include the ability to think, reason, solve puzzles, make judgements and learn and communicate on its own.
Type II
1. Reactive machines
Systems do not store memories or past experiences for future actions. These machines only focus on current scenarios and react to them as per the best possible action.
2. Limited Memory
These machines can store past experiences or some data for a short period of time. These machines can use stored data for a limited time.
3. Theory of mind
It should understand human emotions and beliefs and be able to interact socially like humans. This type of artificial intelligence is still not developed, but researchers are making a lot of efforts and improvements to develop such AI machines.
4. Self awareness
It is the future of AI; the machines will be super intelligent and will have their own consciousness, sentiments, and self-awareness. These machines will be smarter than human minds.
Real life examples of AI
AI can be noticed in every field some examples are:
- Smart home systems.
- Smart cars.
- Google assistant.
- ChatGPT.
- Face Recognition
What is Machine Learning?
Machine Learning is the field of study that gives computers the ability to learn without being explicitly programmed.
-Arthur Samuel,1959
More engineering oriented:
A computer program is said to learn from experience E with respect to some task T and some performance measure P, if its performance on T, as measured by P, improves with experience E.
-Tom Mitchell, 1997
Machine learning is a subset of artificial intelligence.
Types Of ML
There are so many different types of machine learning systems that is useful to classify them into broad categories, based on the following criteria:
How they are supervised during training
1. Supervised Learning
In supervised learning, the training set you feed to the algorithm includes the desired solutions, called labels.
2. Unsupervised Learning
In unsupervised learning, the training data is unlabeled. The system tries to learn without a teacher.
3. Semi-supervised Learning
Since labeling data is time-consuming and costly, you will often have plenty of unlabeled instances, and few labeled instances. Some algorithms can deal with data that’s partially labeled. This is semi-supervised learning.
4. Self-supervised Learning
Another approach to machine learning involves actually generating a full labeled dataset from a fully unlabeled one. Again, once the whole dataset is labeled, any supervised learning algorithm can be used. This approach is called self-supervised learning.
5. Reinforcement Learning
The learning system, called an agent, can observe the environment, select and perform actions, and get rewards in return (or penalties in the form of negative rewards. It must then learn by itself what is the best strategy, called a policy, to get the most reward over time. A policy defines what action the agent should choose when it is in a given situation.
Whether or not they can learn incrementally on the fly
1. Batch Learning
In batch learning, the system is incapable of learning incrementally: it must be trained using all the available data. This will generally take a lot of time and computing resources, so it is typically done offline. First, the system is trained, and then it is launched into production and runs without learning anymore; it just applies what it has learned. This is called offline learning.
2. Online Learning
In online learning, you train the system incrementally by feeding it data instances sequentially, either individually or in small groups called mini-batches. Each learning step is fast and cheap, so the system can learn about new data on the fly, as it arrives.
Whether they work by simply comparing new data points to known data or by detecting patterns
1. Instance-based learning
The system learns the examples by heart, then generalizes to new cases by using a similarity measure to compare them to the learned example(or a subset of them). It works by observing the majority of elements and then classified it in that class.
2. Model-based learning
It is most used type and in this a model is built from a set of examples and then that model is used to make predictions. For selecting the best model there is need of performance measure by which the decision can be made.
Real life examples of ML
- Spam classification.
- Recommendation systems.
- Speech recognition.
- Medical diagnosis.
- Predictive analytics.
What is Deep Learning?
Deep Learning is a subset of machine learning algorithm and it is needed because in machine learning when we give a large amount of data then after some point the machine learning algorithms fails to generalize the data for new data points.
Deep learning uses an Artificial Neural Network(ANN) which is a replica of the human nervous system.
Types of neural networks
1. Feedforward neural network
These are the simplest form of neural network and in this there is a linear flow of information through the neural networks.
2. Convolutional neural network(CNN)
These are majorly used for image and videos recognition tasks, they are able to automatically learn features from images.
3. Recurrent neural network(RNN)
RNN are able to maintain an internal state that captures previous input results so it is used for sequential and time series data.
Real life examples of deep learning
- Facial recognition.
- Speech recognition.
- Machine translation.
- Sentiment analysis.
- Computer vision.
Conclusion
When to choose AI, ML, or DL it purely depends on the data and according to it we can make decision and train our machine.
Follow me and subscribe to catch any updates from me instantly.
Thank you :)