Machine learning is the sub-branch of artificial intelligence that focuses on developing models and algorithms that let the computer learn from the data without being explicitly programmed for each task. In simple words, we can say that it teaches the system to think and understand as humans by learning from data.
Let’s initially start with the types of learning techniques
1. Supervised Learning
2. Unsupervised Learning
3. Reinforcement Learning
Supervised Learning
It is a type of learning where a model learns from labeled data, where the input has a corresponding output. The model can predict whether the output is reliable, reducing error and improving accuracy.
It can be used in classification and regression of the data.
In the classification of data
1. Collect labeled data.
2. Split the Dataset
3. Train the model
4. Validate the model
5. Deploy the model
Within the collective set of types, applying the algorithms and processing it gives the expected output with good accuracy.
Unsupervised learning
It is a type of machine learning where the model works with unlabeled data. It means the pattern is grouped by similar data and hidden structures without human usage. It can be used for tasks like clustering and rule learning, working with supervised learning.
Selecting the algorithm
Train the model on Raw data
Group or Transfer Data
Interpret and User Results
Reinforcement Learning
It is a type of machine learning that focuses on how agents learn with a trial-and-error approach, which needs to maximise cumulative rewards. This allows the machine to learn by interacting with an environment and receiving feedback in the form of rewards.
It has some core components like
1. Policy
2. Reward Signal
3. Value Function
4. Model
5. Implementing Libraries.
