مبانی هوش مصنوعی و یادگیری عمیق

1.1. History of AI

14:28

2.1. AI, ML, and Deep learning

13:18

3.1. Applications of artificial intelligence and types of AI

16:14

4.1. Supervised and Unsupervised Learning

12:04

1.2. Getting started in scikit-learn with iris dataset

29:18

2.2. Image as a data

21:00

3.2. Persian digit dataset

18:11

4.2. Persian digit classification

19:07

5.2. generalization, overfitting, and underfitting

14:30

1.3. Linear Regression

15:18

2.3. Linear Models and Regularization methods

25:45

3.3. Unsupervised learning(Transformations)

11:57

4.3. Unsupervised learning(Clustring)

12:07

5.3. Cross validation, Model complexity and Gridsearch

39:30

6.3. Model Evaluation and Confusion matrix

06:32

1.4. What is perceptron and introduction to neural network

15:44

2.4. Nonlinearity,activation function, and cost function

20:11

3.4. Optimization, gradient descent, and backpropagation

23:39

4.4. How define a model in Keras and tensorflow

15:09

5.4. Batch, Mini-Batch and Stochastic Gradient decent

15:40

6.4. Simple Neural Network in Keras

20:31

7.4. Sparse label, from logits and flatten layer

18:01

8.4. Overfitting and dropout

16:41

1.5. A brief history of CNN

17:08

2.5. Layer hirarchy in convolutional neural network

17:31

3.5. Convolution kernel

17:35

4.5. Padding and stride in convolution

14:43

5.5. Convolution on rgb image and simple network

21:10

6.5. Average and max pooling operation

10:24

7.5. LeNet-5 architecture

05:29

1.6. Calculating the number of Parameters and shapes in CNNs

12:07

2.6. Convolution Neural Network in Tensorflow Keras

06:25

3.6. Learning rate

08:59

4.6. Batch Normalization

18:48