Machine Learning (ML) is a field of Artificial Intelligence (AI) where computers learn from data to make decisions without explicit programming. Instead of writing code, algorithms identify patterns and make predictions from the data.
There are types of Machine Learning.
- Supervised Learning
- Reinforcement Learning
- Unsupervised Learning
What is Supervised Learning
As the name suggests, in supervised learning, we provide the machine with both data and labels during training, so it can understand and learn from the given data. We train the algorithm on a labelled dataset. It means that each training example is paired with an output label. The goal is for the algorithm to learn a mapping from inputs to outputs so it can predict the production of new, unseen data.
What is Unsupervised Learning
In unsupervised learning, the machine is provided with only data and no supervision is given. We do not provide labels to the machine. It involves training an algorithm on data without labelled responses. The goal is to find hidden patterns or intrinsic structures in the input data.
What is Reinforcement Learning
A type of machine learning where an agent learns to make decisions by trying different actions and receiving feedback. In RL, the agent accepts rewards for good actions and penalties for bad ones, and over time, it learns the best way to achieve its goals by maximizing the rewards.
This method is used in various applications like game-playing, robotics, and self-driving cars.
Some examples of Supervised Learning
Example 1: If the input is an audio clip, and AI’s job is to output the text transcript, then this is speech recognition.
Input (A)
Audio
Output (B)
Text
Application Speech Recognition
Example 2: If you want to input English and have it output a different language Al-Arabia, Urdu something else, then this is a machine translation.
Application Machine Translation
Example 3: All the large online ad platforms have a piece of artificial intelligence that inputs some information about an ad and some information about you and tries to predict, whether you click on this ad or not.
Input (A)
Ad + User info
Output (B)
Click???
Example 4: If you want to build a self-driving car, one of the key pieces of AI is the AI that takes as input an image, and some information from Radar, or other sensors and outputs the position of other cars, so your self-driving car can avoid the other cars.
Input (A)
Image, radar info
OUTpUT (B)
Position of other cars
Self-driving Car
Example 5: In Manufacturing, we take as input a picture of something you have just manufactured, such as a picture of a cell phone coming off the assembly line, and you want to output, is there a scratch or there a dent or some other defect on this thing You have just manufactured?. This visual inspection helps manufacturers to reduce or prevent defects in the things that they are making.
Machine Learning frameworks
- TensorFlow
- PyTorch
- Keras
- MXNet
- CNTK
- Caffe
- PaddlePaddle
- Scikit-learn
- R
- Weka
Research publications: Arxiv
Open-source repositories: GitHub
Key Algorithms
Linear Regression
Linear regression is a simple yet powerful algorithm for predicting a continuous output variable based on one or more input features. It assumes a linear relationship between the input variables and the output.
- Example: Predicting a person’s weight based on their height.
Decision Trees
They use Decision Trees for both classification and regression tasks. They work by splitting the data into subsets based on the value of input features. This process is repeated recursively, resulting in a tree-like model of decisions.
- Example: Classifying whether an email is spam or not based on its content.
K-Nearest Neighbors (KNN)
K-Nearest Neighbors is a simple, instance-based learning algorithm for classification and regression. It finds the K closest training examples to a new data point. It makes predictions based on the majority class (for classification) or average (for regression) of these neighbours.
Example: Recommending movies to a user based on similar user preferences.