مبانی هوش مصنوعی و یادگیری عمیق

1.1. History of AI

00:14′

2.1. AI, ML, and Deep learning

00:13′

3.1. Applications of artificial intelligence and types of AI

00:16′

4.1. Supervised and Unsupervised Learning

00:12′

1.2. Getting started in scikit-learn with iris dataset

00:29′

2.2. Image as a data

00:21′

3.2. Persian digit dataset

00:18′

4.2. Persian digit classification

00:19′

5.2. generalization, overfitting, and underfitting

00:14′

1.3. Linear Regression

00:15′

2.3. Linear Models and Regularization methods

00:25′

3.3. Unsupervised learning(Transformations)

00:11′

4.3. Unsupervised learning(Clustring)

00:12′

5.3. Cross validation, Model complexity and Gridsearch

00:39′

6.3. Model Evaluation and Confusion matrix

00:06′

1.4. What is perceptron and introduction to neural network

00:15′

2.4. Nonlinearity,activation function, and cost function

00:20′

3.4. Optimization, gradient descent, and backpropagation

00:23′

4.4. How define a model in Keras and tensorflow

00:15′

5.4. Batch, Mini-Batch and Stochastic Gradient decent

00:15′

6.4. Simple Neural Network in Keras

00:20′

7.4. Sparse label, from logits and flatten layer

00:18′

8.4. Overfitting and dropout

00:16′

1.5. A brief history of CNN

00:17′

2.5. Layer hirarchy in convolutional neural network

00:17′

3.5. Convolution kernel

00:17′

4.5. Padding and stride in convolution

00:14′

5.5. Convolution on rgb image and simple network

00:21′

6.5. Average and max pooling operation

00:10′

7.5. LeNet-5 architecture

00:05′

1.6. Calculating the number of Parameters and shapes in CNNs

00:12′

2.6. Convolution Neural Network in Tensorflow Keras

00:06′

3.6. Learning rate

00:08′

4.6. Batch Normalization

00:18′