Autoplay
Autocomplete
HTML5
Flash
Player
Speed
Previous Lecture
Complete and continue
Deep Learning : Neural Networks with Python
Introduction to Deep Learning
Introduction of Deep Learning and Neural Network (6:13)
Types & Applications on NN, Skills required (4:06)
Software and Libraries for Neural Network
Why Python is best for Neural Network (3:02)
Anaconda Installation: Spyder a Jupyter Notebook (6:24)
Introduction to Keras and Tensorflow (3:55)
Installation of Keras & Tensorflow (5:16)
Summary of python
Introduction to Python (3:32)
Data Tpyes (9:13)
Explaination of Conditional Statement, Loops and Function (4:31)
OOPs (4:17)
Practical Implementation (5:07)
Artificial Neural Network (ANN)
ANN and Neuron Structure (5:14)
How does Neural Network works (3:27)
Practical Implementation of ANN (12:38)
Train Test splitting (6:34)
ANN Implementation
ANN model training (5:21)
Activation Function (3:35)
Fit all the Layers (6:22)
Backpropogation (5:10)
Fitting to the training dataset and finding accuracy (12:29)
Convolution Neural Network (CNN)
Image reading and CNN Process (4:55)
Steps of CNN (6:04)
Conclusion of CNN Process (3:25)
Importing required libraries (6:52)
Reading Cat & Dog Dataset (5:59)
Applying CNN layers (11:05)
Fitting the dataset in Model (5:35)
Visualization of Accuracy & Loss (8:46)
Prediction with single image (15:26)
Recurrent Neural Network (RNN)
Introduction and Application (4:29)
Process of RNN, Types of RNN, Gradient Problem (11:58)
LSTM & GRU Explanation (7:00)
Steps of LSTM (4:07)
Google stock market training dataset reading (6:50)
Creation of data structure with timesteps (10:23)
LSTM layers (8:20)
Google stock market training dataset reading (8:22)
Visualization of stock market trend (10:04)
Introduction and Application
Lecture content locked
If you're already enrolled,
you'll need to login
.
Enroll in Course to Unlock