4.6.1: Multi-layer perceptrons for classification

Channel:
United States Google for Developers
Subscribers:
2,510,000
Published on ● Video Link: https://www.youtube.com/watch?v=BqiOc7iCut0


Duration: 11:28
439 views
17

Up until now you learnt about how to solve regression problems. In this video you will switch hats to solve classification problems - that is what class something belongs to. Learn how to handle data with thousands of inputs such as images, where each pixel is a feature, and instead of regression to predict a number you will solve a classification problem to predict what class an image belongs to. This video covers what classification is and how to create an image classifier for the MNIST dataset that can classify handwritten digits that works via TensorFlow.js right in the web browser introducing new concepts such as 1-hot encodings to represent your class data and categorical cross entropy.

Catch more episodes from Machine Learning for Web Developers (Web ML) → https://goo.gle/learn-WebML
Check out TensorFlow on YouTube → https://goo.gle/TensorFlow-YouTube
Subscribe to Google Developers → https://goo.gle/developers

Connect with Jason Mayes to ask questions:
LinkedIn → https://goo.gle/3GwgeLw
Twitter →https://goo.gle/3Xh6MT7
Discord →https://goo.gle/3WWVO5t

Use #WebML to share your learnings and creations from this course to meet your peers on social media!

See what others have already made with Web ML → http://goo.gle/made-with-tfjs



Other Videos By Google for Developers


2023-02-09Connect, learn, and grow with Google Developer Student Clubs
2023-02-085.2: Make your own Teachable Machine for image classification - transfer learning on the web in JS
2023-02-085.3: Using layers models for transfer learning
2023-02-075.1: Transfer learning: Retraining existing models in the web browser with TensorFlow.js
2023-02-06Google Summer of Code 2023 #Shorts
2023-02-06Google Summer of Code 2023, Cloud Workstations, and more dev news
2023-02-06What does it mean to be a Google Developer Expert (GDE)?
2023-02-064.7.2: Beyond perceptrons: Convolutional Neural Network (CNNs) - Implementation with TensorFlow.js
2023-02-064.7.1: Beyond perceptrons: Convolutional Neural Network (CNNs) in the web browser
2023-02-064.6.2: Multi-layer perceptrons for classification - Implementing a classifier in TensorFlow.js
2023-02-064.6.1: Multi-layer perceptrons for classification
2023-02-064.5.2: Multi-layer perceptrons - Deep neural networks for non linear data
2023-02-064.5.1: Multi-layer perceptrons - The limits of a single neuron
2023-02-064.4.3: Implement a neuron for linear regression - Model creation and training
2023-02-064.4.2: Implement a neuron for linear regression - Importing and normalizing training data
2023-02-064.4.1: Implement a neuron for linear regression - Training data and outliers
2023-02-064.3.2: How to train a neuron?
2023-02-064.3.1: What's a neuron?
2023-02-064.2: Gathering, refining, and using data effectively for ML model datasets
2023-02-034.1: Rolling your own Web ML models from a blank canvas
2023-02-02Interview with Pavlo Stavytskyi, Android contributor to Google Dev Library


Tags:
Google
developers
machine learning for web developers
ml for web developers ml web dev
web machine learning
web ml
tensorflow
tensorflow.js
machine learning course
tensorflow.js course
machine learning courses for web developers
introduction to machine learning with javascript