What you will learn
Building Neural Networks with Tensorflow
Description
You’re going to learn the most popular library to build networks and machine learning algorithms.
In this hands-on, practical course, you will be working your way through with Python, Tensorflow, and Jupyter notebooks.
What you will learn:
- Basics of Tensorflow
- Artificial Neurons
- Feed Forward Neural Networks
- Activations and Softmax Output
- Gradient Descent
- Backpropagation
- Loss Function
- MSE
- Model Optimization
- Cross-Entropy
- Linear Regression
- Logistic Regression
- Convolutional Neural Networks (with examples)
- Text and Sequence Data
- Recurrent Neural Networks (with examples)
- Neural Style Transfer (in progress)
English
language
Content
Lessons
Artificial Neurons
Feed Forward Networks and Activations
Softmax Output
Gradient Descent
Backpropagation
Basics of TensorFlow – 1
Basics of TensorFlow – 2
Computational Graph, Ops, Sessions, Placeholders
Loss Function, MSE, Cross Entropy
Linear Regression
Logistic Regression
Handwriting Recognition with MNIST
Convolutional Neural Networks – 1
Convolutional Neural Networks – 2
Convolutional Neural Networks – 3
Convolutional Neural Networks – 4
Convolutional Neural Networks – 5
Convolutional Neural Networks – 6
CNN and Cifar10 – 1
CNN and Cifar10 – 2
CNN and Cifar10 – 3
CNN and Cifar10 – 4
CNN and Cifar10 – 5
Tactics to Improve the Model
Text and Sequence Data – Intro
Recurrent Neural Networks – 1
Recurrent Neural Networks – 2
Recurrent Neural Networks – 3
Recurrent Neural Networks – 4
Recurrent Neural Networks – 5
Recurrent Neural Networks – 6
Recurrent Neural Networks – 7
Recurrent Neural Networks – 8
In Progress
Neural Style Transfer with VGG19 – 1
Neural Style Transfer with VGG19 – 2
Neural Style Transfer with VGG19 – 3
Neural Style Transfer with VGG19 – 4
Conclusion
Get in Touch