Machine Learning: a new era of learning
Let’s make machines learn.
Machine learning has been one of the most prominent buzzwords in recent years, often used interchangeably with Artificial Intelligence which is another hot topic in the technology industry and then there is Deep learning. So what is the difference between all the three, or are they all the same?
The terms may vary from person to person, however, for me, Artificial intelligence is something that exactly mimics human behaviors like reasoning, generalizing, learning, knowledge, remembering and so on, whereas Machine learning is a subset of it that only deals with how the computers can learn from the data, ML more focus on generalization and pattern recognition and based on that it predicts for future occurrences.
Now the Deep learning is a subset of machine learning which uses machine learning algorithms to generalize, though its architecture is built on a neural network, so it’s used for comparing things like cat vs dog or comparing different shapes and so on.
Now that we have learned the difference between the three, Artificial Intelligence, Machine Learning And Deep learning, let us deep-dive into machine learning and know how it changes over a period of time.
“Learning is any process by which a system improves performance from experience. Machine Learning is concerned with computer programs that automatically improve their performance through experience.”
Here experience is data. In today’s era, we have an enormous number of data generated from different platforms like social media, sensors and many more. So we fed in the inputs (the data) and the outputs to the computer to learn and generalize the output and based on that ML algorithms program themselves to generate future predictions.
Though that is not how we use to program the machines in Nineteen-nineties and Two-thousands, There is something called a heuristics-based or also known as a rules-based approach that was used. In which we give a whole lot of rules to the computer to understand the input and return the output based on that. So it’s very hard for us to write a whole bunch of programs on the other hand Machine learning made it so easy to generalize it on their own from the previous data (experience) and can easily predict the output.
Different types of Machine Learning:-
As with any method, there are different ways to train machine learning algorithms, each with their own advantages and disadvantages. To understand the pros and cons of each type of machine learning, we must first look at what kind of data they take. In ML, there are two kinds of data — labeled data and unlabeled data.
Labeled data has both the input and output parameters in a completely machine-readable pattern, but requires a lot of human labor to label the data, to begin with. Unlabeled data only has one or none of the parameters in a machine-readable form. This negates the need for human labor but requires more complex solutions.
Now let’s discuss the different types of machine learning.
1. Supervised Learning:- Supervised learning is a type of predictive machine learning in which the data comes with labels, where the label is the target we are interested in predicting.
In the above figure, where the dataset is formed by images of dogs and cats, and the labels in the image are ‘dog’ and ‘cat’, the machine learning model would simply use previous data in order to predict the label of new data points. This means, if we bring in a new image without a label, the model would guess if the image is of a dog or a cat, thus predicting the label of the data point. This is precisely how supervised learning works. The model first remembers the dataset of dogs and cats, then formulates a model for what is a dog and what is a cat, and when a new image comes in, the model makes a prediction about what the label of the image is, namely, is it a dog or a cat.
Now, notice that in we have two types of datasets, one in which the labels are numbers (the weight of the animal), and one in which the labels are states, or classes (the type of animal, namely cat or dog). This gives rise to two types of supervised learning models.
Regression models: These are the types of models that predict a number, such as the weight of the animal. We call the output of a regression model continuous, since the prediction can be any real value, picked from a continuous interval.
Classification models: These are the types of models that predict a state, such as the type of animal (cat or dog). We call the output of a classification model discrete, since the prediction can be a value from a finite list. Now the output can be more than two states as well. If we had more states, say, a model that predicts if a picture is of a dog, a cat, or a bird, we can still use a discrete model. These models are called multivariate discrete models. There are classifiers with many states, but it must always be a finite number.
2. Unsupervised Learning:- Unsupervised learning has data which is neither classified nor labeled. Well, it is a dataset with only features, and no target to predict. For example, if our housing dataset had no prices, then it would be an unlabeled dataset. If our emails dataset had no labels, then it would simply be a dataset of emails, where ‘spam’ and ‘no spam’ is not specified.
Let’s go back to the cats and dogs example. If our dataset has no labels, then we simply have a bunch of pictures of dogs and cats, and we do not know what type of pet each one represents. Our model can still tell us if two pictures of dogs are similar to each other, and different to a picture of a cat. Maybe it can group them in some way by similarity, even without knowing what each group represents, this is what Unsupervised learning do.
The two main branches of unsupervised learning are clustering and dimensionality reduction. They are defined as follows.
Clustering: This is the task of grouping our data into clusters based on similarity.
Dimensionality reduction: This is the task of simplifying our data and describing it with fewer features, without losing much generality.
3. Reinforcement learning:- Reinforcement learning is a different type of machine learning, It is about taking suitable action to maximize reward in a particular situation. In reinforcement learning no data is given, It is employed by various software and machines to find the best possible behavior or path it should take in a specific situation. Instead of data, an environment is given, and an agent who is supposed to navigate in this environment. The agent has a goal, or a set of goals. The environment has rewards and punishments, which guide the agent to take the right decisions in order to reach its goal.
In above figure we see a grid world with a robot on the bottom left corner. That is our agent. The goal is to get to the treasure chest in the top right of the grid, with many hurdles in between. The agent is supposed to find the best possible path to reach the reward. The robot learns by trying all the possible paths and then choosing the path which gives him the reward with the least hurdles. Each right step will give the robot a reward and each wrong step will subtract the reward of the robot. The total reward will be calculated when it reaches the final reward that is the diamond.
This ends the brief introduction of Machine Learning, Hope you guys got the intuition of it. Now let’s start making our machines learn that eases our task.
