12. One-shot learning for teaching neural networks to classify objects never seen before
Using Keras/TensorFlow for one-shot learning, we’ll classify objects we’ve never seen before. We’ll train on pairs of objects and identify “are these two things the same?” This is a highly generalizable technique that unlocks cool new applications of deep learning. Follow along with Lukas using the Python scripts here: https://github.com/lukas/ml-class/tre... This is part of a long, free series of tutorials teaching engineers to do deep learning. Leave questions below, and check out more of our class videos: Class Videos: https://wandb.ai/site/tutorials Weights & Biases: https://wandb.ai/site
▶︎
What is Zero-Shot Learning?
▶︎
But what is a neural network? | Deep learning chapter 1
▶︎
13. Speech Recognition with Convolutional Neural Networks in Keras/TensorFlow
▶︎
Siamese Networks | Face Recognition | Computer Vision on Humans
▶︎
Few-Shot Learning (1/3): Basic Concepts
▶︎
Few Shot Learning - EXPLAINED!
▶︎
The Quantile Trick
▶︎
1: Introduction to Neural Networks and Deep Learning; Training Deep NNs
▶︎
1. Build Your First Machine Learning Model
▶︎
C4W4L02 One Shot Learning
▶︎
The Strange Math That Predicts (Almost) Anything
▶︎
Inside Anthropic, the $965 Billion AI Juggernaut | The Circuit
▶︎
Siamese Neural Networks: Explanation and Implementation in TensorFlow / Keras
▶︎
Meta-Learning and One-Shot Learning
▶︎
Few-Shot Learning (2/3): Siamese Networks
▶︎
Few-Shot Learning with Reptile - Keras Code Examples
▶︎
ADL4CV:DV - Siamese Networks and Similarity Learning
▶︎
Gradient descent, how neural networks learn | Deep Learning Chapter 2
▶︎
LSTM is dead. Long Live Transformers!
▶︎