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.
Master advanced ML/DS statistics
·
Module 10
Neural Network Foundations
Neural Networks: Linear Transformations and Activation Functions
Describe a neural network as a composition of linear transformations and non-linear activation functions.
2
Understanding Activation Functions: ReLU and Sigmoid
Explain the purpose of common activation functions like ReLU and Sigmoid.
3
Backpropagation and Gradient Descent in Neural Networks
Train a simple neural network using backpropagation and gradient descent.
"Interpreting Loss Curves for Overfitting and Underfitting"
Diagnose overfitting and underfitting by analyzing training and validation loss curves.
Dropout for Overfitting Prevention
Apply dropout regularization to prevent overfitting in neural networks.
6
Batch Normalization for Stable and Fast Training
Apply batch normalization to stabilize and accelerate training.
7
Tuning Learning Rate and Network Size
Implement a basic hyperparameter tuning process for learning rate and network size.
Previous module
Bayesian Methods for Machine Learning
Next module
Advanced Neural Network Architectures