Skip to main content
grasp.study
About
Explore
Pricing
Log in
Try it for free
Back to course
👋
Welcome to a Grasp lesson
Create a free account
to keep studying and create your own study path.
ML for QA automation
·
Module 5
Deep Learning: Code as Data with Embeddings
1
Code-Aware Tokenization with CodeBERT and GraphCodeBERT
Tokenize source code using a code-aware tokenizer (e.g., from CodeBERT or GraphCodeBERT).
2
Code Embedding with Transformers
Generate semantic embeddings for code snippets using a pre-trained transformer model.
Code Function Similarity with Cosine Embeddings
Compute semantic similarity between code functions using cosine similarity on their embeddings.
4
Visualizing Code Embeddings with Dimensionality Reduction
Visualize code embeddings using dimensionality reduction (e.g., t-SNE, UMAP) to identify clusters.
Code Embeddings for Downstream Tasks
Use code embeddings as input features for a downstream classification or ranking task.
Previous module
Classical ML: Building Predictive Models
Next module
Deep Learning: LLMs for Code Generation & Analysis