CloudAcademy
  1. Home
  2. Training Library
  3. Big Data
  4. Courses
  5. Getting Started With Deep Learning: Working With Data: Gradient Descent

Exercise 3

Developed with
Catalit
play-arrow
Start course
Overview
DifficultyBeginner
Duration1h 45m
Students113

Description

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

 

Transcript

Hey guys, welcome back. In this video, I will review exercise three in section four. And this exercise asks you to compare your results on the Pima Indian data set classification, with the results presented in a notebook on the calico website. In this website, they use different machine learning techniques and they built a model to predict the same outcome you are trying to predict. So the question you're asked is are neural networks better or worse in this particular case? And you can try comparing your results also with the few models from psychic learn for example, a support vector machine or a random forest, and on the exact same train/test split. 

So I'm not going to tell you if the performance is worse or better, that's for you to find out. Also, we ask you to try restricting your features to only four features like in the suggested notebook. And how does the model performance change? You can test this for your model, the neural network, but also for the models like the random forest and the support vector machine. So, try to do the exercise first, and then feel free to watch the solution in the next video. Good luck.

About the Author

Students737
Courses8
Learning paths3

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 Université de Paris VI and graduated from Singularity University summer program of 2011.