IT class - September 7th [Community Learning Week •Phase 6] Activity

【Answer】1. B    2. AB    3. C    4. C    5. A

【Winner】Vien,    Loti_fa,    thi_bay,    S_Noch,   CyberTec

----------------------

Hello, everyone!

Join the Community Learning week IT class! 

IT class learning time of this phase: September 6th – September 11th.

Answer time of this class: September 7th, 8 AM - September 8th, 4 PM (UTC+0).

Class topic

Post 1. Machine Learning Training Method: Gradient Descent Method

Gradient descent is a first-order iterative optimization algorithm for finding a local minimum of a differentiable function. The idea is to take repeated steps in the opposite direction of the gradient (or approximate gradient) of the function at the current point because this is the direction of steepest descent. Conversely, stepping in the direction of the gradient will lead to a local maximum of that function; the procedure is then known as gradient ascent.…(More)

Post 2. Machine Learning Training Methods: Hyperparameters

For example, you need to set the learning rate (learning rate), iterations (number of gradient descent cycles),(number of hidden layers),(number of hidden layer units), and choice of the activation function.…(More)

Post 3. Machine Learning Training Methods: Cross-Validation

The basic idea of Cross-Validation is to divide the original dataset into two parts: a training set and a validation set. Train the classifier using the training set and test the model using the validation set to check the classifier performance.…(More)

Post 4. Machine Learning Algorithms: Linear Regression

Linear regression: a statistical analysis method to determine the quantitative relationships between two or more variables through regression analysis in mathematical statistics.…(More)

Post 5. Machine Learning Algorithms: Logistic Regression

Both the logistic regression model and linear regression model are generalized linear models. Logistic regression introduces nonlinear factors (the sigmoid function) based on linear regression and sets thresholds, so it can deal with binary classification problems.…(More)

Class Q&As

After attending this class, please answer all the following questions and submit. Once submitted, the answer cannot be modified.

Click to learn: >>>  previous class - Cloud & Big Data      >>> Next class - Intelligent Collaboration