Зміст курсу

Introduction to Neural Networks

1. Concept of Neural Network

What is a Neural Network?Neural Network Structure What is a Neuron?Activation Functions Forward and Backward Propagation Applications of Deep Learning in the Real World

2. Neural Network from Scratch

Single Neuron Implementation Perceptron Layers Forward Propagation Backward Propagation Data Preprocessing Model Training and Evaluation Neural Network with scikit-learn

3. Conclusion

Neural Networks or Traditional Models Other types of Neural Networks Manual Hyperparameter Tuning Automatic Hyperparameter Tuning Final Quiz Summary

Introduction to Neural Networks

Manual Hyperparameter Tuning

Завдання

Until now, we have used the neural network only for the classification task. Now try to solve the regression problem using MLPRegression.

To do this, we will get the real world California Housing dataset and try to teach the model to predict median home value for households in tens of thousands of US dollars. Your goal is to have the Mean Absolute Error (MAE) be less than 0.4.

Experiment with the hidden layers (use 1-2 hidden layers with 10-30 neurons for each).
Experiment with the number of epochs (change number of epochs from 10 to 50).
Experiment with the learning rate (change it in from 0.0001 to 1).

Make sure your MAE is less than 0.4 before submitting.

Все було зрозуміло?

Секція 3. Розділ 3

Зміст курсу

Introduction to Neural Networks

1. Concept of Neural Network

What is a Neural Network?Neural Network Structure What is a Neuron?Activation Functions Forward and Backward Propagation Applications of Deep Learning in the Real World

2. Neural Network from Scratch

Single Neuron Implementation Perceptron Layers Forward Propagation Backward Propagation Data Preprocessing Model Training and Evaluation Neural Network with scikit-learn

3. Conclusion

Neural Networks or Traditional Models Other types of Neural Networks Manual Hyperparameter Tuning Automatic Hyperparameter Tuning Final Quiz Summary

Introduction to Neural Networks

Manual Hyperparameter Tuning

Завдання

Until now, we have used the neural network only for the classification task. Now try to solve the regression problem using MLPRegression.

Experiment with the hidden layers (use 1-2 hidden layers with 10-30 neurons for each).
Experiment with the number of epochs (change number of epochs from 10 to 50).
Experiment with the learning rate (change it in from 0.0001 to 1).

Make sure your MAE is less than 0.4 before submitting.

Все було зрозуміло?

Секція 3. Розділ 3