A progressive learning path introducing the mathematical, computational, and conceptual foundations of neural networks, followed by practical model building, evaluation, and application. Because no grade level or curriculum framework was specified, standard-code alignment is left unspecified.
8 topics · 0 questions total
Students will learn how neural networks use input data and target labels. They will practice identifying useful features, separating training and testing data, recognizing data quality problems, and understanding how class imbalance, missing values, and biased samples affect model performance. Students will also distinguish between supervised, unsupervised, and reinforcement learning contexts.
Google Machine Learning: Data Representation, Datasheets for Datasets, Dataset Exploration Notebook
You're previewing 2 of 8 topics. Create a free account to view the full syllabus, questions, and add resources to your plan.
Sign in for freeNo credit card required
We use cookies to detect your location for personalized content and to improve your experience with analytics. You can choose which cookies to allow.