Tommy @Shaughnessy119 · 28 May 2023
Summing this all up, Stephen shares an image showing the training process for a neural net and how the loss function should decrease over time. If the loss eventually streamlines, yay you have a solid model If it not you can't rely on it and it's time to change the architecture https://t.co/Yg4dRHX4MO
58 709Views
56Likes
5Reposts
1Replies
0Quotes
6Bookmarks
Is that a lot?
28.2×vs this author's median2 084 views is typical
100Percentile for this authorof 5 recent posts
19.8×vs 10K–100K median2 968 views is typical
84.00%Reachviews ÷ followers
0.11%Engagement rateof viewers reacted