...
Full Bio
Google Go Language Future, Programming Language Programmer Will Get Best Paid Jobs
124 days ago
New Coder Tool Promises to Turbo-Charge Coding In Major Programming Language
125 days ago
Why Many Companies Plan To Double Artificial Intelligence Projects In The Next Year
125 days ago
Why 75% SMBs Are Not Worried About Artifical Intelligence Killing Their Jobs
125 days ago
Interview Study Guide for Data Science To Get Job Quickly
128 days ago
Highest Paying Programming Language, Skills: Here Are The Top Earners
641382 views
Top 10 Best Countries for Software Engineers to Work & High in-Demand Programming Languages
494421 views
Which Programming Languages in Demand & Earn The Highest Salaries?
447489 views
50+ Data Structure, Algorithms & Programming Languages Interview Questions for Programmers
264819 views
100+ Data Structure, Algorithms & Programming Language Interview Questions Answers for Programmers - Part 1
226278 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.