Talks
Speakers
Events
Topics
Sign in
Home
Talks
Speakers
Events
Topics
Leaderboard
Use
Analytics
Sign in
Suggest modification to this talk
Title
Description
RubyConf AU 2018 | Sydney | Australia March 8th & 9th, 2018 Organisers: Melissa Kaulfuss (@melissakaulfuss), Nicholas Bruning (@thetron), Sharon Vaughan (@Sharon_AV) & Nadia Vu (@nadiavu_) MCs: Melissa Kaulfuss & Nicholas Bruning Sponsored by: Envato, Culture Amp, Lookahead, Reinteractive, Oneflare, Shippit, Twilio, The Conversation, Netflix, Disco, Heroku, REA Group
Date
Summarized using AI?
If this talk's summary was generated by AI, please check this box. A "Summarized using AI" badge will be displayed in the summary tab to indicate that the summary was generated using AI.
Show "Summarized using AI" badge on summary page
Summary
Markdown supported
In the video titled "Machine Learning Explained to Humans (Part 1)" presented at RubyConf AU 2018 by Paolo Perrotta, the speaker aims to demystify the concept of machine learning for developers. He acknowledges the common frustrations faced by those new to the field and seeks to simplify complex topics using relatable examples and intuitive explanations. Key points discussed include: - **Understanding Machine Learning**: Perrotta shares his initial confusion and how traditional resources often cater to researchers rather than developers seeking practical insights. He emphasizes that this talk is intended for those wanting to grasp the foundational concepts of machine learning. - **Example of a Pizzeria**: To illustrate the principles, he uses a small restaurant that wants to predict pizza sales based on reservation data. He explains that the relationship between these variables needs to be understood to forecast sales accurately. - **Linear Regression**: The core method introduced is linear regression, which involves mapping input variables (reservations) to output variables (pizza sales) using a simple equation. He describes how to collect data, visualize it, and determine a line of best fit to make predictions. - **Parameters in Linear Regression**: Perrotta discusses the parameters involved—weight (W) and bias (B)—and formalizes the equation of the line, showing how these parameters help infer the predicted output (pizza sales) based on input data (reservations). - **Loss Function**: The concept of loss is introduced as a measure of error in predictions. By constructing a mean squared error function, the goal is to minimize this loss, allowing for better predictions. - **Gradient Descent**: This fundamental algorithm is explained as a method to iteratively adjust W and B using calculated gradients to reach the optimal parameters, minimizing prediction errors effectively. Overall, the video provides a basic yet practical overview of machine learning, focusing on making the concepts relatable to software developers. Perrotta concludes by reinforcing that while the mathematics may seem intimidating, the underlying principles are accessible and essential for further exploration in artificial intelligence. This informative session highlights the importance of understanding the basics of machine learning in a developer-friendly manner, paving the way for deeper insights into artificial intelligence.
Suggest modifications
Cancel
