Neural network on categorization of animals using python

Question

I want to know how young children categorize animals. What features (colour, amount of legs, etc) are they using to identify what the animal is. For example, if they were exposed to a white dog previously, how can they tell that a white cat is not a dog. what do they use as their indicators? I want to have different images such as a different colour dog, a polar bear, white cat, white bunny, etc. I want my model to be a multi-layer perceptron trained using backpropagation, with just 1 input and 1 output layer. I would like the output layer to be "dog".How would I go about doing this given my question and also how would I code the pictures as an input. Is this even possible. What would be my steps in explanation form

Answer 1

I do not have any expertise in Python. However, the question at hand is about discrimination of stimuli. Children, when first introduced to a stimulus (white dog), will categorize that stimulus. Now, if they see any stimulus that holds similar characteristics such as a polar bear (white, similar shaped face, four legs, ect..) they typically will identify it as a dog. There are multiple cognitive psychology theories that hypothesize how this happens, but I digress. However, this get's interesting because children have also been known to associate fish or other animals as "dogs" as well. Correction is needed to address that the polar bear is different from the dog. When differentiating they may make connections that dogs bark, cats meow and have a different face, bunnies hop and have a short tail and long ears. The way a child chooses to differentiate varies based on what differences are presented to them, what they notice on their own, and what animals they already have in their repertoire (current knowledge). When provided with correction and differences they are able to build new neural pathways and categorize them more accurately. I hope this answers the first half of your question.