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

## Gradient descent
We have learned that gradient descent helps reduce error by derivating the error with respect to weight. We add the weight change to the initial weight and continue updating it until we reach the bottom of the slope where the error is minimum.






The **weight update** can occur in a _batch_ or a _stochastic_  manner. Learn about each of them in the following sections:


SGD picks up a “random” instance of training data at each step and then computes the gradient. Consequently, it is becomes faster because there is less data to manipulate at a single time.

There is a drawback to the stochastic nature of the SGD, i.e., when it reaches close to the minimum value. The result is that it does not settle down but bounces back and settles for a good value rather than optimal values for parameters.  




Learn about the stochastic vs. batch update nature of the gradient descent.

✨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

Gradient Descent: Stochastic vs. Batch Update

Gradient descent

Stochastic gradient