Predicting the future isn't magic, it's Artificial Intelligence.

Basics of deep learning Lecture 3 is about data ethics, It's self Explanatory and Rachel’s Lecture is more than sufficient.  Lecture 4 is more about breaking the myth behind neural networks. And the basics of pytorch and how fastai api makes deep learning cool. You may come across jargon like Sigmoid, Relu, Stochastic Gradient Descent, Learning rate and so on. Their explanation is great. They explained maths with a piece of code and I completely enjoyed it. What i would suggest is play with notebook 4 and learn more things. In case you don't understand something, go through it again and again and you will catch up. If you want some help ask the question in the forum. You can practise lecture 4 by downloading the repository and going to the clean folder, there is only code not with a prose. It's the best place to practise what you have learned till now. The motto is, If you are in doubt, run the code .

Introduction: Last time what we saw is Linear regression which is helpfull in predicting the data which is in certain patern but Logistic regression helpfull in classification problem. For example, whether the person having diseases or not ,whether will rain tommorow or not. Exploraory data analysis: In this phase we usually check the rows and columns of the given data sets and describe it and check wheather the data containing missing value or not. Seperate the numerical columns and categorical columns and split the data into train,val,test test to generalize the model prediction.  Data Visualization : Here we are analysing the co-relation of data. which is helpfull in building the better model. Actually I build a logistic regression model on breast cancer detection and weather prediction which is good for the people who are beginning the carrier in data science. Data Preprocessing : Imputing: Filling the missing value with appropriate technique. Scaling: Scaling is used to reduce...