AI-ML [Part-1]: Introduction to Artificial Intelligence & Machine Learning

Artificial Intelligence (AI) and its branch, Machine Learning (ML), are helping to make new technology that changes how we live and work. In this blog series, I’ll share my journey into AI so we can learn together. This first post is the start of the series.

What is Artificial Intelligence (AI)

Artificial Intelligence (AI) refers to the simulation of human intelligence in machines that are programmed to think and learn like humans. AI enables machines to perform tasks that typically require human intelligence, such as problem-solving, decision-making, speech recognition, and visual perception.

AI can be classified into various types, but mainly by capability and functionality.

1. Based on Capability

A. Narrow AI: It is designed for very specific tasks, it can perform a specific dedicated task with intelligence, like recognizing faces or playing chess, but it can't do anything outside of that specific task.

B. General AI: General AI is a type of AI that can think and learn like a human, able to do many different tasks, but we haven't built it yet, it is still under research.

C. Super AI: Super AI would be smarter than humans at everything, but it's just an idea right now and doesn't exist, it is just a hypothetical concept.

2. Based on Functionality

A. Reactive Machine: A Reactive Machine can only respond to the present moment, like a chess computer that makes moves based on the current board.

B: Limited memory: Limited Memory AI can remember things for a short time, like a self-driving car that remembers recent road conditions to make decisions.

C: Theory of Mind: Theory of Mind AI would understand people's emotions and thoughts, but this kind of AI is still being researched.

D: Self-Aware AI: AI that can recognize others' emotions, plus have its thoughts and feelings, but this is only science fiction for now. This is the final stage of AI.

The Role of Data in AI

Data is the lifeblood of AI. Data is very important for AI because it helps them learn and make decisions. Here are three types of data:

• Structured Data: This data is organized neatly in tables, like a list of names and addresses in a spreadsheet.
• Unstructured Data: This data doesn’t have a set format and includes things like text, pictures, or videos, like social media posts or photos.
• Semi-structured Data: This data is a bit organized but not as strict as structured data, like information in a JSON or XML file.

What is Machine Learning (ML)?

Machine Learning (ML) is a subset of AI that focuses on the development of algorithms that enable machines to learn from data and improve their performance over time. Unlike traditional programming, where a machine follows a set of predefined rules, ML allows machines to identify patterns and make decisions based on data inputs (models). Two of the most common classes of machine learning models are:

1. Supervised ML Models: In Supervised Learning, the model is trained on a labeled (data where each item has a label or category attached to it) dataset, where each input is paired with the correct output. The goal is for the model to learn the mapping from inputs to outputs so that it can predict the output for new, unseen data. Supervised Learning is widely used in applications such as image recognition, speech recognition, fraud detection, and medical diagnosis.
2. Unsupervised ML Models: In Unsupervised Learning, the model is given an unlabeled (data where the items don't have any labels or categories attached) dataset and must find patterns, structures, or relationships within the data. Unlike Supervised Learning, there is no predefined output, and the model learns from the inherent structure of the data. Unsupervised Learning is commonly used in customer segmentation, market basket analysis, anomaly detection, and recommendation systems.

What is Deep Learning?

Deep Learning is a subset of Machine Learning that uses neural networks with many layers to analyze and understand complex data. It’s inspired by how the human brain works and is especially good at handling tasks like image and speech recognition. Two deep learning model types are:

1. Discriminative Deep Learning Models: These models, like Convolutional Neural Networks (CNNs) used for image classification, focus on differentiating between categories. They learn the boundaries between different classes.
2. Generative Deep Learning Models: These models, such as Generative Adversarial Networks (GANs), aim to create new data samples that resemble the training data. They learn the underlying distribution of the data and generate new, similar examples.

Conclusion

Artificial Intelligence (AI) and Machine Learning (ML) are changing the world with exciting new solutions. In this series, we'll learn how AI and ML work, and how they are used in real life. Please keep following to explore these exciting topics and see the amazing possibilities they can offer!