HOW CAN I START WITH MACHINE LEARNING!!
1. What is machine learning?
“I think I should learn “what does this sentence mean? Learning is a universal trait which is acquired by every living organism like a bird learn to fly, a tiger learn to hunt their prey etc. But if I say that machine can learn too!! Earlier we wonder that what if we say “Turn On Light “ and the light turns on it was like a dream but that dream came true now ,we are living in an era that machine is no comparatively less than humans. We can teach machine how to learn and also they can learn on their self this is called MACHINE LEARNING.
In mathematics especially Probability, statistics leads a major role in machine learning .As machine can predict the future and tell the probability of a certain event by performing several calculations and applying algorithm.
2. Why machine learning and uses
If I talk in layman language then machine learning is like a paint which can be applied on any surface.Similarly machine learning can be used in plethora domains. Some of the domain are:-
These problem statement are taken from kaggle (will discuss later)
- Healthcare: Predicting patient diagnostics for doctors to review
- Social Network: Predicting certain match preferences on a dating website for better compatibility
- Finance: Predicting fraudulent activity on a credit card
- E-commerce: Predicting customer churn
- Biology: Finding patterns in gene mutations that could represent cancer
3.How to learn machine learning
Machine works just like humans like human learn by observing so as the machine, machine looks for the pattern and learn according to the pattern to make it more intelligent we have to provide it with large data so that it observes different kind of patterns and learns and give the desired output.
We have to give the machine the proper and correct data for instance if you are a police man and your mission is to find the pickpockets then you need the correct data that is the location where he was seen last, his contact details etc. similar it goes with the machine learning, we have to provide it will correct data so that it predict the right result, machine learns from the previous data and make predictions based on previous data.
4. Types of Machine Learning
There are three main categories of machine learning:-
- Supervised learning: The machine learns from labeled (given) data. Normally, the data is labeled by humans.
- Unsupervised learning: The machine learns from un-labeled data. Meaning, there is no “right” answer given to the machine to learn, but the machine must hopefully find patterns from the data to come up with an answer.
- Reinforcement learning: The machine makes mistake and learn from the data.
Supervised Machine Learning
- Supervised learning is the most common and studied type of learning because it is easier to train a machine to learn with labeled data than with un-labeled data. Depending on what you want to predict, supervised learning can used to solve two types of problems: regression or classification.
Regression Problem:
- If you want to predict continuous values, such as trying to predict the cost of a house or the weather outside in degrees, you would use regression. This type of problem doesn’t have a specific value constraint
because the value could be any number with no limits.
• Classification Problem:
- If you’re interested in a problem like: “will there be rain tomorrow” then this is a classification problem because you’re trying to classify the answer into two specific categories: yes or no (in this case the answer is yes to the question above). This is also called a, binary classification problem.
Unsupervised Learning
- In unsupervised learning the aim of the machine is to detect the patterns in the data and group them according to it , the role of human is to give the data to the machine and tell them to find the pattern. It depends on us what we want to group together, unsupervised learning can group data together by:-
A.clustering
B. association
CLUSTRING
- Unsupervised learning tries to solve this problem by looking for similarities in the data. If there is a common cluster or group, the algorithm would then categorize them in a certain form. An example of this is when we get a mail in Gmail then the machine automatically identify that mail as SPAM or HAM and then shift SPAM mails to junk/spam folder. It’s an example of clustering
Generative models
- A generative model could generate new photos of animals that look like real animals, while a discriminative model could tell a dog from a cat. GANs are just one kind of generative model.
- A generative model includes the distribution of the data itself, and tells you how likely a given example is. For example, models that predict the next word in a sequence are typically generative models (usually much simpler than GANs) because they can assign a probability to a sequence of words.
REINFORCEMENT LEARNING
- This type of machine learning requires the use of a reward/penalty system. The goal is to reward the machine when it learns correctly and to penalize the machine when it learns incorrectly, the process is iterative ,it keeps on learning
- Example:-training a model to learning chess, amazon echo (Alexa).
SEMI SUPERVISED LEARNING
Semi-supervised learning is placed between unsupervised and supervised learning models. A semi-supervised learning problem starts with a series of labeled data points as well as some unlabeled data. The main aim of semi supervised learning is to identify the unlabeled dataset based on labeled information set given.
Example of semi supervised learning:-
- Speech analysis: it is a popular example of semi supervised learning .in speech analysis labeling the audio files require a lot of human effort so semi supervised learning makes it easy, it is able to predict the unlabeled music files based on the labeled ones.
TERMINOLOGIES OF MACHINE LEARNING
1. Model:
- A machine learning model is a file that has been trained to recognize certain types of patterns. When you train a model over a set of data, providing it an algorithm that it can use to reason over and learn from those data.
- Once you have trained the model, you can use it to reason over data that it hasn't seen before, and make predictions about those data. For example, let's say you want to build an application that can recognize a user's emotions based on their facial expressions. You can train a model by providing it with images of faces that are each tagged with a certain emotion, and then you can use that model in an application that can recognize any user's emotion.
2. Feature:
- A feature is a measurable property of the object you’re trying to analyze. Thy are the building blocks of datasets. The quality of the features in your dataset has a major impact on the quality of the insights you will gain when you use that dataset for machine learning
3. Target:
- The target variable of a dataset is the feature of a dataset about which you want to gain a deeper understanding. A supervised machine learning algorithm uses historical data to learn patterns and uncover relationships between other features of your dataset and the target.
4. Prediction:
- Suppose we are given a dataset and using the help of those data points we are able to identify the pattern and predict the result .this process is called prediction.
5. Training:
- Whenever you are have the dataset the first thing you do is “exploratory data analysis “and then you divide the dataset into 2 parts “TRAINING AND TEST “dataset. We train our model on test dataset i.e. apply machine learning model and predict the result ,it’s called training after training our model we test our model on “test” dataset and we observe that the result is almost similar to training dataset.
Written By:-Devansh Srivastava