AI, Machine Learning, Deep Learning, and Blockchain Flashcards

Flashcards on AI, Machine Learning, Deep Learning, and Blockchain

What is Artificial Intelligence (AI)?

The branch of computer science dedicated to building systems capable of performing tasks that typically require human intelligence such as reasoning, learning, understanding language, recognizing patterns, solving problems, and adapting to new situations.

What are the two main categories of AI?

Narrow AI (Weak AI) and General AI (Strong AI).

Give some real-world applications of AI.

Healthcare (diagnosis support, drug discovery), Transportation (autonomous vehicles, logistics optimization), Finance (fraud detection, algorithmic trading), Customer Service (chatbots, recommendation systems).

What is Machine Learning (ML)?

A subset of AI involving algorithms that allow computers to learn patterns from data without being explicitly programmed.

List the main types of Machine Learning.

Supervised Learning, Unsupervised Learning, Reinforcement Learning, Self-supervised Learning.

What is Supervised Learning?

A machine is trained on a labeled dataset meaning the data includes both the input and the correct output.

What is Unsupervised Learning?

A machine is given data without labels and must find patterns on its own.

What is Self-Supervised Learning?

A machine learning technique in which models learn by labeling unlabeled data.

What is Reinforcement Learning?

A machine learning method in which an agent learns to make decisions through interactions with its surrounding environment.

What is a 'Model' in Machine Learning?

A mathematical framework that learns to make predictions by identifying patterns in data.

What happens during the 'Training' process in Machine Learning?

Models learn from data, fine-tuning themselves to make accurate predictions.

What are 'Features' in the context of Machine Learning?

Specific measurable traits of the data that help the model understand what it is looking at.

What are 'Evaluation Metrics' in Machine Learning?

Standards used to judge how well a model is performing, including metrics like accuracy and precision.

What is 'Deployment' in Machine Learning?

Taking the trained model and using it to make predictions on new data in real-world applications.

What is 'Continuous Learning' in Machine Learning?

Regularly updating the model with new data to keep it relevant and effective.

What is a 'Loss Function' in Machine Learning?

A tool that helps the model improve by measuring how far off its predictions are from the actual results.

What are 'Hyperparameters' in Machine Learning?

Settings that you configure before training the model, like how fast it learns or how complex it is.

What is Deep Learning?

A machine learning technique that uses artificial neural networks to analyze data, learn patterns, and automate tasks requiring human intelligence.

What are the building blocks of a deep neural network?

Layers, consisting of neurons (nodes or units) that process data and pass it to the next layer (Input layer, hidden layers, output layer).

What is a Loss Function in neural networks?

It measures how well the neural network’s predictions align with the actual target values, acting as a performance metric during training.

Give examples of Loss Functions.

Categorical Cross-Entropy, Sparse Categorical Cross-Entropy, Binary Cross-Entropy

What does an Optimizer do in a neural network?

It updates the network’s weights to minimize the loss function using gradient descent-based algorithms.

What is Blockchain?

A distributed, unchangeable record of transactions in which data is stored in chronologically ordered sections, allowing for safe and transparent transactions without a central authority.

Give examples of Blockchain applications.

Cryptocurrencies (Bitcoin and Ethereum), Supply Chain Tracking, Secure Data Sharing, Healthcare Records, Tamper-proof Digital Elections, Digital Identity.