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

The accuracy of the predicted output can be calculated by comparing it with the target output. This accounts for computing the error.






# Error function (or loss)

## Mean squared error (MSE) 

The error is the difference between the actual value and the predicted value. We want this error value to be minimum to get the best possible function. This error equation is given by:

<center>

$E=y-y'$

</center>

> 📝 Note: Since a negative error
would not make sense, square the error function to force the raw error to be positive by multiplying it
by itself.
<center>

$E=(y-y')^2$</center>

</center>
Here,

- $y$ - the actual output

-  $y'$ - the predicted output 

In practice and to simplify the maths, this error is divided by two:

<center>

$E=\frac{1}{2}(y-y')^2$

 </center>

The error function above is the **mean squared error (MSE)**. the mean squared error is a common choice for _regression problems_.


## Cross entropy (CE)

For _classification_, the best choice is the **cross-entropy.** For a binary classification task:

<center>

$E =$ 
$-(y log(y') + (1-y)log(1-y'))$

</center>

Here,

- $y$ - the actual output

-  $y'$ - the predicted output 

The cross-entropy is also called **log loss**. Minimizing cross-entropy, it maximizes the log-likelihood of a predicted value belonging to a particular class. 

# Code


Learn about the error functions used for classification and regression problems.

✨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

The Error Function

Error function (or loss)

Mean squared error (MSE)