...
Full Bio
Use Machine Learning To Teach Robots to Navigate by CMU & Facebook Artificial Intelligence Research Team
266 days ago
Top 10 Artificial Intelligence & Data Science Master's Courses for 2020
267 days ago
Is Data Science Dead? Long Live Business Science
295 days ago
New Way to write code is about to Change: Join the Revolution
296 days ago
Google Go Language Future, Programming Language Programmer Will Get Best Paid Jobs
617 days ago
Top 10 Best Countries for Software Engineers to Work & High in-Demand Programming Languages
735498 views
Highest Paying Programming Language, Skills: Here Are The Top Earners
670752 views
Which Programming Languages in Demand & Earn The Highest Salaries?
475884 views
Top 5 Programming Languages Mostly Used By Facebook Programmers To Developed All Product
473058 views
World's Most Popular 5 Hardest Programming Language
413685 views
6 Steps To Write Any Machine Learning Algorithm From Scratch: Perceptron Case Study
- What is it?
- What is it typically used for?
- When CAN'T I use this?
- The single layer Perceptron is the most basic neural network. It's typically used for binary classification problems (1 or 0, "yes" or "no").
- It's a linear classifier, so it can only really be used when there's a linear decision boundary. Some simple uses might be sentiment analysis (positive or negative response) or loan default prediction ("will default", "will not default"). For both cases, the decision boundary would need to be linear.
- If the decision boundary is non-linear, you really can't use the Perceptron. For those problems, you'll need to use something different.
- The Elements of Statistical Learning, Section 4.5.1
- Understanding Machine Learning: From Theory To Algorithms, Section 21.4
- Jason Brownlee's article on his Machine Learning Mastery blog, How To Implement The Perceptron Algorithm From Scratch In Python
- Sebastian Raschka's blog post, Single-Layer Neural Networks, and Gradient Descent
- Initialize the weights
- Multiply weights by inputs and sum them up
- Compare the result against the threshold to compute the output (1 or 0)
- Update the weights
- Repeat
- You'll gain an even deeper understanding because you're teaching others what you just learned.
- You can showcase it to potential employers. It's one thing to show that you can implement an algorithm from a machine learning library, but it's even more impressive if you can implement it yourself from scratch.