Setup Menus in Admin Panel

Course Curriculum

Introduction
1.1 Welcome to Machine Learning 00:00:00
1.2 What does the course cover 00:00:00
Neural Networks Intro
2.1 Cross-entropy loss 00:00:00
2.2 Graphical representation 00:00:00
2.3 Introduction to neural networks 00:00:00
2.4 L2-norm loss 00:00:00
2.5 N-parameter gradient descent 00:00:00
2.6 One-parameter gradient descent 00:00:00
2.7 The linear model 00:00:00
2.8 The linear model. Multiple inputs and multiple outputs 00:00:00
2.9 The linear model. Multiple inputs. 00:00:00
2.10 The objective function 00:00:00
2.11 Training the model 00:00:00
2.12 Types of machine learning 00:00:00
Setting Up the Environment
3.1 Installing Anaconda 00:00:00
3.2 Installing TensorFlow 2.0 00:00:00
3.3 Jupyter Dashboard – Part 1 00:00:00
3.4 Jupyter Dashboard – Part 2 00:00:00
3.5 Setting up the environment – Do not skip, please! 00:00:00
3.6 Why Python and why Jupyter 00:00:00
Minimal Example
4.1 Generating the data (optional) 00:00:00
4.2 Initializing the variables 00:00:00
4.3 Outline 00:00:00
Introduction to Tensor flow 2
5.1 A note on coding in TensorFlow 00:00:00
5.7 Types of file formats used in TensorFlow 00:00:00
5.2 Customizing your model 00:00:00
5.3 Interpreting the result and extracting the weights and bias 00:00:00
5.4 Model layout – inputs, outputs, targets, weights, biases, op 00:00:00
5.5 TensorFlow 2 intro 00:00:00
5.6 TensorFlow outline 00:00:00
Deep Nets Overview
6.1 Activation functions 00:00:00
6.2 Backpropagation 00:00:00
6.3 Backpropagation – intuition 00:00:00
6.4 Really understand deep nets 00:00:00
6.5 Softmax activation 00:00:00
6.6 The layer 00:00:00
6.7 What is a deep net 00:00:00
6.8 Why do we need non-linearities 00:00:00
Overfitting
8.1 Early stopping – motivation and types 00:00:00
8.2 N-fold cross validation 00:00:00
8.3 Train vs validation 00:00:00
8.4 Train vs validation vs test 00:00:00
8.5 Underfitting and overfitting 00:00:00
8.6 Underfitting and overfitting. A classification example 00:00:00
Initialization
9.1 Initializaiton 00:00:00
9.2 Types of simple initializations 00:00:00
9.3 Xavier’s initialization 00:00:00
Optimizers
10.1 Adaptive learning schedules 00:00:00
10.2 Adaptive moment estimation 00:00:00
10.3 Learning rate schedules 00:00:00
10.4 Learning rate schedules. A picture 00:00:00
10.5 Local minima pitfalls 00:00:00
10.6 Momentum 00:00:00
10.7 SGD&Batching 00:00:00
Preprocessing
11.1 Basic preprocessing 00:00:00
11.2 Dealing with categorical data 00:00:00
11.3 One-hot vs binary 00:00:00
11.4 Preprocessing 00:00:00
11.5 Standardization 00:00:00
Deeper Example
12.1 How to tackle the MNIST 00:00:00
12.2 Importing the relevant libraries and loading the data 00:00:00
12.3 Learning 00:00:00
12.4 Outline the model 00:00:00
12.5 Preprocess the data – create a validation dataset and scale 00:00:00
12.6 Preprocess the data – shuffle and batch the data 00:00:00
12.7 Select the loss and the optimizer 00:00:00
12.8 The dataset 00:00:00
Business Case
13.1 Balancing the dataset 00:00:00
13.2 Exploring the dataset and identifying predictors 00:00:00
13.3 Learning and interpreting the result 00:00:00
13.4 Load the preprocessed data 00:00:00
13.5 Outlining the business case solution 00:00:00
13.6 Preprocessing the data 00:00:00
13.7 Setting an early stopping mechanism 00:00:00
13.8 Testing the model 00:00:00
Conclusion
14.1 An overview of CNNs 00:00:00
14.2 An overview of RNNs 00:00:00
14.3 Non-NN approaches 00:00:00
14.4 Summary 00:00:00
14.5 Whats more out there 00:00:00

Course Reviews

N.A

ratings
  • 5 stars0
  • 4 stars0
  • 3 stars0
  • 2 stars0
  • 1 stars0

No Reviews found for this course.

PRIVATE COURSE
  • PRIVATE
  • 1 week, 3 days
0 STUDENTS ENROLLED
    Copyright @2019