Great graphics,
If we we dig a little into your maths we we see that your 'activation function' is a binary sum of pixels for each number with each column, and is completely deterministic. In other words there is a direct (one to one) relationship between all possible input and your activation function. To work you have to train (set this relationship) for EVERY number you want to identify, which is not what ANNs usually do. An ANN is used when it is NOT POSSIBLE to provide the training with EVERY possible input-output relationship, and its effectiveness is determined by how it copes with input it has NOT been trained on. ANNs are a bit 'fuzzy', they capture trends and patterns more than direct mathematical relationships.
I'm not sure I have explained my reasoning clearly over the last few posts on this, but I think your work is great. My only suggestion is to maybe read a little on ANNs as well as pursuing your own reasearch, but keep having fun.
If we we dig a little into your maths we we see that your 'activation function' is a binary sum of pixels for each number with each column, and is completely deterministic. In other words there is a direct (one to one) relationship between all possible input and your activation function. To work you have to train (set this relationship) for EVERY number you want to identify, which is not what ANNs usually do. An ANN is used when it is NOT POSSIBLE to provide the training with EVERY possible input-output relationship, and its effectiveness is determined by how it copes with input it has NOT been trained on. ANNs are a bit 'fuzzy', they capture trends and patterns more than direct mathematical relationships.
I'm not sure I have explained my reasoning clearly over the last few posts on this, but I think your work is great. My only suggestion is to maybe read a little on ANNs as well as pursuing your own reasearch, but keep having fun.
![[-]](https://litdev.uk/mybb/images/collapse.png)