Talks
Speakers
Events
Topics
Sign in
Home
Talks
Speakers
Events
Topics
Leaderboard
Use
Analytics
Sign in
Suggest modification to this talk
Title
Description
RailsConf 2017: Is it Food? An Introduction to Machine Learning by Matthew Mongeau Machine Learning is no longer just an academic study. Tools like Tensorflow have opened new doorways in the world of application development. Learn about the current tools available and how easy it is to integrate them into your rails application. We'll start by looking at a real-world example currently being used in the wild and then delve into creating a sample application that utilizes machine learning.
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 "Is it Food? An Introduction to Machine Learning," Matthew Mongeau presents an accessible introduction to machine learning, particularly within the context of Rails applications. This talk was delivered at RailsConf 2017 and aims to bridge the gap between overly technical and simplistic explanations of machine learning concepts. Mongeau begins by noting his personal interest in practical machine learning applications and emphasizes a need for balance in understanding technical concepts. The primary focus is on image classification, specifically determining whether an image is of food. Key points discussed in the video include: - **The Challenge of Image Recognition**: The talk kicks off with a discussion of recognizing images as food and the complexities involved in machine learning concerning image classification. - **Types of Machine Learning**: Mongeau explains three categories of machine learning: unsupervised learning, supervised learning, and reinforcement learning, with an emphasis on supervised learning for image recognition using neural networks. - **TensorFlow and Neural Networks**: He introduces TensorFlow as a powerful framework for building and training neural networks, explaining key concepts such as tensors and data flow graphs. - **Real-World Application at Cookpad**: Mongeau shares a case study drawn from his work at Cookpad, which manages a vast number of images submitted by users. The company needed to ensure that images submitted are indeed food-related, leading to the development of an automated classification system. - **Implementation Steps**: He details the steps of creating a simple Rails application that classifies images as food using a Python backend serviced by Flask, highlighting the importance of using existing frameworks like TensorFlow for practical applications. - **Best Practices and Lessons Learned**: Throughout his journey, Mongeau stresses the significance of utilizing appropriate tools and frameworks, learning from experiences, and adapting processes to facilitate machine learning integration in Rails applications. In conclusion, the core takeaway emphasizes the importance of applying machine learning practically and the necessity of using robust tools such as TensorFlow, especially when building applications in environments like Rails. He advocates for embracing Python for machine learning tasks due to its strong community support and better toolsets. Mongeau ends on a hopeful note that image classification technology will continue to evolve, presenting increasing utility across various industries.
Suggest modifications
Cancel
