Gain insights into deep learning fundamentals, explore perceptron and advanced models, and discover practical coding in NumPy and Keras. Test your knowledge with quizzes and coding challenges.

Dockerfile.tar.gz

keras python

keras python - using models

This beginner level and highly comprehensive course is intended for learners who are familiar with Python programming. You will become familiar with the fundamental concepts and terminologies used in deep learning. In addition, this course will help you understand the importance of deep learning techniques. You will examine simple models like perceptron before learning more complex yet powerful deep learning models. The course will provide hands-on practical knowledge of how to code simple and complex deep learning models in NumPy, a powerful Python library and Keras, a cutting-edge library for deep learning in Python. You can test your knowledge with the quizzes that are provided at the end of every lesson and coding challenges that will help you gain a higher understanding. By the end of the course, you should have a general understanding of the basics in deep learning and you will be equipped with the right tools to learn more advanced concepts.

A Beginner's Guide to Deep Learning

## Problem statement
The preprocessed MNIST dataset has been provided. Specify the network architecture, compile, fit, and evaluate the model performance on the training data.

- The model architecture should have 2 hidden layers with 60 and 60 nodes respectively and an output layer. The activation function for the first hidden layer should be `relu` and it should be `sigmoid for the second hidden layer`. The activation function for the output layer should be `softmax`.

- The model should be compiled with `adam` as an optimizer.

- The model should fit on the training data with 5 `epochs` and `batch_size` equal to 128. 

- Evaluate the model on the training data and check its accuracy.

## Sample input
The preprocessed MNIST data is provided with: 
- Training features: `X_train` 
- Training labels: `Y_train`
- Testing features: `X_train` 
- Testing labels: `Y_train`


## Sample output
The trained model accuracy after defining the model architecture, the compile method, the fit method, and the evaluation model.


## Coding exercise


Write your code below. It is recommended​ to solve the exercise before viewing the solution.

Good luck!🤞

# Problem statement
The preprocessed MNIST dataset has been provided. Specify the network architecture, compile, fit, and evaluate the model performance on the training data.

- The model architecture should have 2 hidden layers with 60 and 60 nodes respectively and an output layer. The activation function for the first hidden layer should be `relu` and it should be `sigmoid for the second hidden layer`. The activation function for the output layer should be `softmax`.

- The model should be compiled with `adam` as an optimizer.

- The model should fit on the training data with 5 `epochs` and `batch_size` equal to 128. 

- Evaluate the model on the training data and check its accuracy.

# Sample input
The preprocessed MNIST data is provided with: 
- Training features: `X_train` 
- Training labels: `Y_train`
- Testing features: `X_train` 
- Testing labels: `Y_train`


# Sample output
The trained model accuracy after defining the model architecture, the compile method, the fit method, and the evaluation model.


# Coding exercise


Write your code below. It is recommended​ to solve the exercise before viewing the solution.

Good luck!🤞

Build the network for the MNIST dataset problem that we examined at in the previous lesson.

✨Before We Begin

✨Introduction to Deep Learning

✨Simple Perceptron Models in NumPY

✨Towards Deep Neural Networks in NumPY

🖥️ Project: Build a Letter Classification Model

Deep Learning in NumPy Exam

✨Building Deep Learning Models with Keras

✨Fine-tune Keras Model

Anomaly Detection in Medical Images: Python, TF, and PyTorch

🖥️ Project: Build a Digit Recognition Model

✨Conclusion

Deep Learning in Keras Exam

Purchase Price Prediction for Used Cars Using Deep Learning

🍀 Challenge: Building the Network

Problem statement