• Unit 1: Introduction
• Unit 2: Supervised Learning
• Unit 3: ML Fundamentals
• Unit 4: Neural Models
• Unit 5: Embeddings
• Unit 6: Generalization
• Unit 7: Vision and Perspectives
• 376 Unit 1: Introduction to Generative Modeling
• 376 Unit 2: Language Modeling
• 376 Unit 3: Architectures
• Neural Computation
• 376 Unit 4: Generation and Prompt Engineering
• ML Systems
• 376 Unit 5: Multimodal Models and Diffusion
• 376 Unit 6: Miscellaneous Topics
• Learning Machines
• Context and Implications
• Review

Unit 5: Embeddings

Students who complete this unit will demonstrate that they can:

Embeddings

• Define the following terms: sample, target, loss, batch, epoch, activation function, layer, overfitting
• Contrast binary, multiclass, and multilabel classification
• Describe the difference between a metric and a loss function.
• Explain how a pre-trained model can be repurposed for a new task by separating it into a general-purpose feature extractor (sometimes called a "body" or "encoder") and a task-specific linear classifier (sometimes called "head").
• Interpret a linear classifier head as computing similarities in a vector space of embedded data items.

Contents