Introduction to Artificial Intelligence and Machine Learning

Artificial Intelligence (AI) and Machine Learning (ML) are two of the most exciting and rapidly growing fields in computer science. In the context of the Professional Certificate in AI and Computational Immunology, these terms have specific meanings that are crucial to understanding the material. Here, we will explain some of the key terms and vocabulary related to AI and ML.

1. Artificial Intelligence (AI)

AI is a branch of computer science that deals with the creation of intelligent agents, which are systems that can perceive their environment and take actions to achieve specific goals. AI involves developing algorithms and models that enable machines to mimic human-like intelligence, including the ability to learn, reason, problem-solve, perceive, and make decisions.

2. Machine Learning (ML)

ML is a subset of AI that focuses on developing algorithms and models that enable machines to learn from data, without being explicitly programmed. ML algorithms can automatically identify patterns and relationships in data, and use this information to make predictions or decisions.

3. Supervised Learning

Supervised learning is a type of ML in which the algorithm is trained on labeled data, which includes both inputs and corresponding outputs. The algorithm uses this data to learn a mapping between inputs and outputs, and can then make predictions on new, unseen data.

4. Unsupervised Learning

Unsupervised learning is a type of ML in which the algorithm is trained on unlabeled data, which includes only inputs, with no corresponding outputs. The algorithm must identify patterns and relationships in the data on its own, without any prior knowledge of the desired output.

5. Reinforcement Learning

Reinforcement learning is a type of ML in which the algorithm learns by interacting with an environment and receiving feedback in the form of rewards or penalties. The algorithm uses this feedback to learn a policy, which is a mapping between states and actions that maximizes the expected reward.

6. Neural Networks

Neural networks are a type of ML algorithm that are inspired by the structure and function of the human brain. They consist of interconnected nodes, or artificial neurons, that process information in parallel and learn from data through a process called backpropagation.

7. Deep Learning

Deep learning is a subset of neural networks that involves training large, complex models on massive amounts of data. These models can learn hierarchical representations of data, and can achieve state-of-the-art performance on a wide range of tasks, including image and speech recognition, natural language processing, and game playing.

8. Activation Function

An activation function is a mathematical function that is applied to the output of a neural network node, or artificial neuron. The activation function determines whether the node should be activated, or fired, based on the input it receives. Common activation functions include the sigmoid, tanh, and ReLU functions.

9. Loss Function

A loss function is a mathematical function that measures the difference between the predicted output of a model and the true output. The loss function is used during training to adjust the model's parameters, or weights, to minimize the difference between the predicted and true outputs.

10. Gradient Descent

Gradient descent is an optimization algorithm that is used to minimize the loss function of a model. It involves iteratively adjusting the model's parameters in the direction of the negative gradient of the loss function, which is the direction of steepest descent.

11. Overfitting

Overfitting is a common problem in ML in which a model learns too closely to the training data, and fails to generalize to new, unseen data. Overfitting can be avoided by using regularization techniques, such as L1 and L2 regularization, dropout, and early stopping.

12. Bias-Variance Tradeoff

The bias-variance tradeoff is a fundamental concept in ML that refers to the tradeoff between the complexity of a model and its ability to generalize to new data. A model with high bias is overly simplistic, and will underfit the data, while a model with high variance is overly complex, and will overfit the data.

13. Cross-Validation

Cross-validation is a technique for evaluating the performance of a model on new, unseen data. It involves dividing the data into k folds, or subsets, and training and testing the model k times, with each fold serving as the test set