Learning with Limited Labeled Data with Shioulin Sam - TWiML Talk #255
The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
00:00
Estimating Uncertainty with Dropout
This chapter explores the complexities of uncertainty estimation in deep neural networks, focusing on the use of Bayesian networks and dropout during inference. It highlights how enabling dropout can create multiple neural network samples, facilitating the computation of prediction probabilities and informing active learning strategies.
Transcript
Play full episode
