A "single-layer" perceptron can't implement XOR. Check the following link (see the section Perceptron for XOR)
http://computing.dcu.ie/~humphrys/Notes/Neural/single.neural.html
How can we implement an LRU cache using just a single container i.e. map or unordered_map?
Expected operations: 1. find(key_t) - find a certain value in cache 2. insert(key_t, value_t) - insert a new value to the cache