Training and inference phases of neural networks can be analysed individually.
For back propagation or training:
O(n^5) where n is the number of neurons, number of layers and number of iterations.
For forward propagation or inference:
# For a string | |
# 'youremywholeworld' | |
a = input() | |
# For single integer input | |
# 9 | |
a = int(input()) | |
# For multiple (small) input | |
# 8 9 |
# cook your dish here | |
graph = { | |
0: [1, 2], | |
1: [2], | |
2: [0], | |
3: [2] | |
} | |
# no of nodes | |
n = 4 |
#include <vector> | |
#include <set> | |
#include <unordered_set> | |
#include <cassert> | |
#include <iostream> | |
#include <ctime> | |
#include <unistd.h> | |
#include <chrono> | |
#include <algorithm> | |
#include <vector> |
""" | |
a) Images generated by the microscope | |
. . . . . . . . . . | |
. . . . . * . . . . | |
. . . * * * * . . . | |
. . * * * * * . . . | |
* * * * * * * . . . | |
. . * * * * * . . . | |
. . * * * . . . . . |