Learn about the importance of gradient descent and backpropagation, under the umbrella of Data and Machine Learning, from Cloud Academy.
From the internals of a neural net to solving problems with neural networks to understanding how they work internally, this course expertly covers the essentials needed to succeed in machine learning.
Learning Objective
- Understand the importance of gradient descent and backpropagation
- Be able to build your own neural network by the end of the course
Prerequisites
- It is recommended to complete the Introduction to Data and Machine Learning course before starting.
Hey guys, welcome back. In this video, we'll review exercise one of section four. In exercise one of section four, we're asked to predict whether or not some people will be diagnosed diabetes from a set of variables of exams. So this is the population of Pima Indians. It's a very famous dataset that we got from UCI and it contains information about the patients including pregnancies, glucose, blood pressure, and then a few other medical examinations, and the last column is the outcome which is a binary variable. So it's a classification problem, and you're guided through a series of steps that go from loading the data, creating a histogram to inspect the features, and exploring the correlations between the features and the outcome column. We suggest using the seaborn pairplot, but you can also draw a heat map as we saw in the lecture.
Then there are a few open questions. Do features need standardization? And if so, what kind? Are we gonna use MinMax or standard? And then finally, prepare x and y using a machine learning model. Do you need dummy columns? And make sure you define your target variable. So as usual, try to do the exercise first, and then feel free to watch the video with the solution. Good luck.
I am a Data Science consultant and trainer. With Catalit I help companies acquire skills and knowledge in data science and harness machine learning and deep learning to reach their goals. With Data Weekends I train people in machine learning, deep learning and big data analytics. I served as lead instructor in Data Science at General Assembly and The Data Incubator and I was Chief Data Officer and co-founder at Spire, a Y-Combinator-backed startup that invented the first consumer wearable device capable of continuously tracking respiration and activity. I earned a joint PhD in biophysics at University of Padua and UniversiteĢ de Paris VI and graduated from Singularity University summer program of 2011.