This course module teaches fundamental concepts and best practices for working with numerical data, from how data is ingested into a model using feature vectors to feature engineering techniques such as normalization, binning, scrubbing, and creating synthetic features with polynomial transforms.| Google for Developers
This course module teaches the basics of neural networks: the key components of neural network architectures (nodes, hidden layers, activation functions), how neural network inference is performed, how neural networks are trained using backpropagation, and how neural networks can be used for multi-class classification problems.| Google for Developers
This course module teaches the fundamentals of logistic regression, including how to predict a probability, the sigmoid function, and Log Loss.| Google for Developers
This course module provides an overview of language models and large language models (LLMs), covering concepts including tokens, n-grams, Transformers, self-attention, distillation, fine-tuning, and prompt engineering.| Google for Developers
This course module teaches the fundamentals of linear regression, including linear equations, loss, gradient descent, and hyperparameter tuning.| Google for Developers
This course module teaches the key concepts of embeddings, and techniques for training an embedding to translate high-dimensional data into a lower-dimensional embedding vector.| Google for Developers
This course module teaches the fundamentals of binary classification, including thresholding, the confusion matrix, and classification metrics such as accuracy, precision, recall, ROC, AUC, and prediction bias. A brief intro to multi-class classification is provided at the end of the module.| Google for Developers
This course module teaches the fundamental concepts and best practices of working with categorical data, including encoding methods such as one-hot encoding and hashing, creating feature crosses, and common pitfalls to look out for.| Google for Developers
This course module teaches best practices for using automated machine learning (AutoML) tools in your machine learning workflow, including benefits and limitations and common AutoML patterns that can be used in projects.| Google for Developers
Machine learning (ML) powers some of the most important technologies we use,| Google for Developers
Learn how to interpret an ROC curve and its AUC value to evaluate a binary classification model over all possible classification thresholds.| Google for Developers
Gemini 2.5 Pro is our most advanced model for complex tasks. With thinking built in, it showcases strong reasoning and coding capabilities.| Google DeepMind
DO NOT EDIT.| TensorFlow
Two-dimensional, size-mutable, potentially heterogeneous tabular data.| pandas.pydata.org
LaMDA adds pieces to one of the most tantalizing sections of the language puzzle: conversation.| Google
