Discover fundamental deep learning concepts, master coding models using NumPy and Keras, and test your knowledge with quizzes and coding challenges. Gain insights into effective deep learning techniques.

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 sonar data for this challenge is taken from [UCI](https://archive.ics.uci.edu/ml/datasets/Connectionist+Bench+(Sonar,+Mines+vs.+Rocks)) Repository of datasets. Train a network to distinguish between sonar signals bouncing off of a metal cylinder and those bouncing off of a roughly cylindrical rock.


Each bouncing signal pattern is a set of 60 numbers between 0.0 and 1.0. Each number represents the energy within a particular frequency band that is integrated over a certain period of time. The label associated with each record contains the letter "R" if the object is a rock and "M" if it is a mine (metal cylinder).

Train the model with the configuration provided below:

- The model architecture should have 2 hidden layers with 30 and 60 nodes respectively and an output layer. The activation function of the hidden layers should be `relu`. The activation function of the output layer should be `sigmoid`.

- The model should be compiled with `adam` as an optimizer, loss as `binary_crossentropy`, and `metrics=['accuracy']`.

- The model should fit on the training data with 20 epochs and 10 batch size. Store the result in the `history` variable.

- Evaluate the model on the training data and store the `loss` and `accuracy`.




# Sample input

> 📝 Note: The data is already read and the features and labels are separated in `train_X` and `train_y` respectively. 

- _Line 5_: Reads the dataset `sonar.csv` using the `read_csv` function of the pandas data frame.

- _Line 9_: Reads the features in `train_X`.

- _Line 24_: Reads the labels in `train_y`.







 

In this challenge, classify whether the given sonar is a mine or a rock.

✨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

🖥️ Project: Build a Digit Recognition Model

✨Conclusion

Deep Learning in Keras Exam

🍀 Challenge: Mine vs. Rock Classifier

Problem statement