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

# Why is optimization hard?

The optimal value of one weight depends on the value of the other weights. Many weights are optimized at once. From the slope, we will understand which weights to increase or decrease. However, the updates may not improve the model meaningfully. This calls for changing the hyperparameters.




## Model Parameter vs. Hyperparameter

Model parameters are **internal parameters** of the model. In the case of a neural network, model parameters are neuron weights. They are learned automatically while training the network. These weight parameters are then utilized to make predictions.


Hyperparameters are **external parameters** of the model. They are set by the programmer of the model. This includes selecting the activation function, the optimizer, the batch size, and the epochs. Hyperparameters have a significant impact on the accuracy of a neural network.

# Hyperparameters: Optimization methods

There are various ways to optimize the hyperparameters using trial and error. However, there is not a consensus on what works best. 


## Hyperparameters related to a neural network structure

**1. Model complexity** 

 This defines hidden layers or nodes per layer. The increase in model complexity usually enhances accuracy. 

> 📝 Learn more about [model complexity](https://www.educative.io/courses/beginners-guide-to-deep-learning/model-capacity).





**2. Dropout** 

This defines
the number of neurons that will be randomly killed to prevent the network from learning the intrinsic details of the training data samples.

This lesson will introduce the idea of model optimization.

✨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

Introduction to Model Optimization

Why is optimization hard?

Hyperparameters: Optimization methods

Hyperparameters related to a neural network structure