|
|
|
|
|
|
by turnersr
2167 days ago
|
|
|
Thank you for this. As someone who who understands linear algebra well, I feel the neural network formalism obfuscates the core meaning of these processes. It's good for describing composition, but not good for understanding the parts in-between. Looking forward to your take on LSTMs and transforms ;). Much thanks! Great contribution. |
|
|