This shows you the differences between two versions of the page.
Both sides previous revision Previous revision | Next revision Both sides next revision | ||
publications [2019/12/28 14:54] admin |
publications [2019/12/28 14:56] admin |
||
---|---|---|---|
Line 4: | Line 4: | ||
Notable achievements: | Notable achievements: | ||
- | * Deep Neural Networks were first used for my [[#mphil86|1986 MPhil thesis]] - these had the form o_i = f(\sum_n^i-1 w_ij o_j) and so were very deep having only one unit per layer, yet trained well as they had skip connections stretching back to the input. | + | * 1986: Deep Neural Networks were first used for my [[#mphil86|MPhil thesis]] - these had the form o_i = f(\sum_n^i-1 w_ij o_j) and so were very deep having only one unit per layer, yet trained well as they had skip connections stretching back to the input. |
IN PROGRESS: Email me if you want a copy of something that doesn't yet have a PDF. | IN PROGRESS: Email me if you want a copy of something that doesn't yet have a PDF. |