Where'd My Gradient Go? It Vanished!
ซีรีส์ที่ถูกเก็บถาวร ("ฟีดที่ไม่ได้ใช้งาน" status)
When? This feed was archived on May 02, 2025 14:13 (). Last successful fetch was on November 09, 2024 13:09 ()
Why? ฟีดที่ไม่ได้ใช้งาน status. เซิร์ฟเวอร์ของเราไม่สามารถดึงฟีดพอดคาสท์ที่ใช้งานได้สักระยะหนึ่ง
What now? You might be able to find a more up-to-date version using the search function. This series will no longer be checked for updates. If you believe this to be in error, please check if the publisher's feed link below is valid and contact support to request the feed be restored or if you have any other concerns about this.
Manage episode 446714678 series 3605861
This video discusses the vanishing gradient problem, a significant challenge in training deep neural networks. The speaker explains how, as a neural network becomes deeper, gradients—measures of how changes in network parameters affect the loss function—can decrease exponentially, leading to a situation where early layers of the network are effectively frozen and unable to learn. This problem arises because common activation functions like the sigmoid function can produce very small derivatives, which compound during backpropagation. The video then explores solutions like using different activation functions (like ReLU) and architectural changes (like residual networks and LSTMs) to mitigate this issue.
Watch the video: https://www.youtube.com/watch?v=ncTHBi8a9uA&pp=ygUSdmFuaXNoaW5nIGdyYWRpZW50
71 ตอน