This course provides a hands-on learning experience on training deep learning models using TensorFlow and Google Colab. By the end of the course, students will be able to differentiate between deep learning and machine learning, understand neural network architecture, activation functions, loss functions, backpropagation, recurrent neural networks, LSTM cells, text data encoding, convolutional neural networks (CNN), and techniques to improve model accuracy such as dropout layers and data augmentation. The course uses a tutorial series approach and is designed for beginners interested in deep learning and neural networks.
Overview
Syllabus
How to Train Deep Learning Model on Google Colab for FREE | Train Neural Network on GPU Machine.
Google Colaboratory for free GPU -(Neural Network Model Training) | Part 2.
Differentiate between Deep Learning and Machine Learning | Tensorflow Tutorial Series.
Tensorflow Tutorial Series Introduction | A Hands-on Learning Experience.
What is Deep Learning | Tensorflow Tutorial Series.
Artificial Neural Network Tutorial | Tensorflow Tutorial Series.
Activation Functions in Neural Networks | Tensorflow Tutorial Series.
How Neural Network gets Trained | Tensorflow firsthand Tutorial Series for Beginners.
Google Colaboratory for Tensorflow | Tensorflow firsthand Tutorial Series for Beginners.
Tensorflow Math Operations using Constants | Tensorflow Tutorial Series.
How Data travels in Deep Neural Networks | Scalar vs Vector vs Matrix vs Tensor.
What are Placeholders in Tensorflow | Usage of Placeholders in Tensorflow.
Tensorflow Variables and Associated Computations | Optimize Model parameter during Training.
What is Loss Function in Deep Learning | Loss Function in Machine Learning | Loss Function Types.
Backpropagation Explained in a simple manner | Backpropagation in Neural Networks.
Learning from the past events using Recurrent Neural Network | A Gentle introduction to RNN.
Basic Building Blocks of Recurrent Neural Network | Recurrent Neural Network (RNN/LSTM).
Cases where Backpropagation fails in Neural Networks | Inherent problems with Recurrent Neural Net.
Why Long Memory Neurons are Important in Recurrent Neural Network | Deep Learning.
Understand LSTM cells to build Neural Network based Applications | LSTM Architecture.
Convert Text into Numeric Encoding for Recurrent Neural Network | How RNN read Text Data.
Convolution Neural Network (CNN) Introduction and Intuition | Convolution Neural Network Explained.
How to Detect Features of an Image using CNN (Convolution Neural Network)?.
Why Rectified Linear Unit (ReLU) is required in CNN? | ReLU Layer in CNN.
Why do we use max POOLING Layer in CNN | What is Pooling Layer in CNN?.
Why do we use Flattening Layer in CNN | What is Flattening Layer in CNN?.
How to address Overfitting in Neural Network using Dropout Layer | What is Dropout Layer in CNN?.
What is Fully Connected Layer | How does Fully Connected Layer works.
How to Utilize Pre-Trained Models for building Deep Learning Models | VGG16 ResNET Object Detection.
Increase ACCURACY of Model on Small Dataset | DATA AUGMENTATION for Small Image Dataset.
Taught by
The AI University
