Section 1 : Introduction
|
Lecture 1 | INTRODUCTION TO BRAINMEASURES PROCTOR SYSTEM |
Section 2 : Artificial Intelligence Basics
|
Lecture 1 | Why to learn artificial intelligence and machine learning | 00:04:11 Duration |
|
Lecture 2 | Introduction to machine learning | 00:06:05 Duration |
Section 3 : Installing Deep Learning Library
|
Lecture 1 | Installing Java | 00:04:12 Duration |
|
Lecture 2 | Installing Eclipse | 00:03:58 Duration |
|
Lecture 3 | Installing Maven | 00:03:23 Duration |
|
Lecture 4 | Cloning the libraries from Github | 00:03:08 Duration |
Section 4 : Multi-Layer Neural Networks (Deep Learning) Theory
|
Lecture 1 | Deep neural networks | 00:05:33 Duration |
|
Lecture 2 | Activation functions | 00:09:54 Duration |
|
Lecture 3 | Loss functions | 00:05:58 Duration |
|
Lecture 4 | Gradient descent stochastic gradient descent | |
|
Lecture 5 | Hyperparameters | 00:05:19 Duration |
Section 5 : Deep Neural Networks Implementation
|
Lecture 1 | Deep neural network implementation - XOR problem | 00:11:19 Duration |
|
Lecture 2 | Deep neural network implementation - XOR problem II | 00:05:34 Duration |
|
Lecture 3 | Deep neural network implementation - iris dataset | 00:06:03 Duration |
|
Lecture 4 | Deep neural network implementation - iris dataset II | 00:03:21 Duration |
|
Lecture 5 | ARTICLE Optimizers Explained (SGD, ADAGrad, ADAM |
Section 6 : Convolutional Neural Networks Theory
|
Lecture 1 | Convolutional neural networks basics | 00:06:06 Duration |
|
Lecture 2 | Feature selection | 00:04:17 Duration |
|
Lecture 3 | Convolutional neural networks - kernel | 00:04:18 Duration |
|
Lecture 4 | Convolutional neural networks - kernel II | 00:05:48 Duration |
|
Lecture 5 | Convolutional neural networks - pooling | 00:05:51 Duration |
|
Lecture 6 | Convolutional neural networks - flattening | 00:05:02 Duration |
|
Lecture 7 | Convolutional neural networks - illustration | 00:02:39 Duration |
Section 7 : Convolutional Neural Networks Implementation
|
Lecture 1 | CNN implementation I - digit classification | 00:05:20 Duration |
|
Lecture 2 | CNN implementation II - digit classification | 00:07:17 Duration |
|
Lecture 3 | CNN implementation III - digit classification | 00:06:45 Duration |
|
Lecture 4 | Emoji classification I - handling custom datasets | 00:07:22 Duration |
|
Lecture 5 | Emoji classification II - the dataset | 00:03:39 Duration |
|
Lecture 6 | Emoji classification III - convolutional network | 00:03:24 Duration |
|
Lecture 7 | Emoji classification IV - test | 00:03:58 Duration |
|
Lecture 8 | ARTICLE Regularization (L1, L2 and dropout) |
Section 8 : Recurrent Neural Networks Theory
|
Lecture 1 | Why do recurrent neural networks are important | 00:04:34 Duration |
|
Lecture 2 | Recurrent neural networks basics | |
|
Lecture 3 | Vanishing and exploding gradients problem | |
|
Lecture 4 | Long-short term memory (LTSM) model | |
|
Lecture 5 | Gated recurrent units (GRUs) | 00:03:27 Duration |
Section 9 : Recurrent Neural Networks Implementation
|
Lecture 1 | Google's approach word2vec method | 00:07:21 Duration |
|
Lecture 2 | Skip-Gram model fundamentals | 00:11:53 Duration |
|
Lecture 3 | Text classification implementation - similar words | 00:09:10 Duration |
|
Lecture 4 | Sentiment analysis implementation I | 00:06:11 Duration |
|
Lecture 5 | Sentiment analysis implementation II | 00:07:01 Duration |
|
Lecture 6 | Sentiment analysis implementation III | 00:04:55 Duration |
|
Lecture 7 | Sentiment analysis implementation IV |
Section 10 : Course Materials (DOWNLOADS)
|
Lecture 1 | Course materials |