XOR - birinchi ishlaydigan tarmoq

import numpy as np


def sigmoid(z):
    return 1.0 / (1.0 + np.exp(-z))


class Tarmoq:
    def __init__(self, olchamlar, urug=42):
        gen = np.random.default_rng(urug)
        self.olchamlar = olchamlar
        self.qatlamlar = len(olchamlar) - 1
        self.W, self.b = [], []
        for i in range(self.qatlamlar):
            chegara = np.sqrt(2.0 / olchamlar[i])
            self.W.append(gen.normal(0, chegara, (olchamlar[i], olchamlar[i + 1])))
            self.b.append(np.zeros(olchamlar[i + 1]))

    def oldinga(self, X):
        A = X
        kesh = {"A0": X}
        for i in range(self.qatlamlar):
            Z = A @ self.W[i] + self.b[i]
            A = sigmoid(Z) if i == self.qatlamlar - 1 else np.tanh(Z)
            kesh[f"Z{i+1}"] = Z
            kesh[f"A{i+1}"] = A
        return A, kesh

    def orqaga(self, y, kesh):
        n = len(y)
        dW = [None] * self.qatlamlar
        db = [None] * self.qatlamlar
        dZ = (kesh[f"A{self.qatlamlar}"] - y) / n
        for i in range(self.qatlamlar - 1, -1, -1):
            dW[i] = kesh[f"A{i}"].T @ dZ
            db[i] = dZ.sum(axis=0)
            if i > 0:
                dZ = (dZ @ self.W[i].T) * (1.0 - kesh[f"A{i}"] ** 2)
        return dW, db

    def yangilash(self, dW, db, tezlik):
        for i in range(self.qatlamlar):
            self.W[i] -= tezlik * dW[i]
            self.b[i] -= tezlik * db[i]

    def yoqotish(self, X, y, eps=1e-12):
        A, _ = self.oldinga(X)
        A = np.clip(A, eps, 1 - eps)
        return float(-np.mean(y * np.log(A) + (1 - y) * np.log(1 - A)))


X_xor = np.array([[0.0, 0.0], [0.0, 1.0], [1.0, 0.0], [1.0, 1.0]])
y_xor = np.array([[0.0], [1.0], [1.0], [0.0]])

t = Tarmoq([2, 1], urug=0)
for _ in range(20000):
    _, kesh = t.oldinga(X_xor)
    dW, db = t.orqaga(y_xor, kesh)
    t.yangilash(dW, db, 0.5)

bashorat, _ = t.oldinga(X_xor)
print("yo'qotish:", round(t.yoqotish(X_xor, y_xor), 6))
print("bashoratlar:", np.round(bashorat.ravel(), 4))
print("kerak:      ", y_xor.ravel())
print("aniqlik:", float(((bashorat > 0.5).astype(float) == y_xor).mean()))

t = Tarmoq([2, 2, 1], urug=3)
for davr in range(20001):
    _, kesh = t.oldinga(X_xor)
    dW, db = t.orqaga(y_xor, kesh)
    t.yangilash(dW, db, 0.5)
    if davr % 5000 == 0:
        print(f"davr {davr:>5}: yo'qotish = {t.yoqotish(X_xor, y_xor):.6f}")

bashorat, _ = t.oldinga(X_xor)
print("bashoratlar:", np.round(bashorat.ravel(), 4))
print("aniqlik:", float(((bashorat > 0.5).astype(float) == y_xor).mean()))

t = Tarmoq([2, 2, 1], urug=0)
for davr in range(20001):
    _, kesh = t.oldinga(X_xor)
    dW, db = t.orqaga(y_xor, kesh)
    t.yangilash(dW, db, 0.5)
    if davr % 5000 == 0:
        print(f"davr {davr:>5}: yo'qotish = {t.yoqotish(X_xor, y_xor):.6f}")

bashorat, _ = t.oldinga(X_xor)
print("bashoratlar:", np.round(bashorat.ravel(), 4))
print("aniqlik:", float(((bashorat > 0.5).astype(float) == y_xor).mean()))

t = Tarmoq([2, 2, 1], urug=0)
for _ in range(20000):
    _, kesh = t.oldinga(X_xor)
    dW, db = t.orqaga(y_xor, kesh)
    t.yangilash(dW, db, 0.5)

_, kesh = t.oldinga(X_xor)
H = kesh["A1"]

print("kirish -> yashirin qatlam:")
for x, h, y in zip(X_xor, H, y_xor):
    print(f"  ({x[0]:.0f}, {x[1]:.0f}) -> ({h[0]:>7.4f}, {h[1]:>7.4f})   XOR = {y[0]:.0f}")

t = Tarmoq([2, 2, 1], urug=0)
for _ in range(20000):
    _, kesh = t.oldinga(X_xor)
    dW, db = t.orqaga(y_xor, kesh)
    t.yangilash(dW, db, 0.5)

_, kesh = t.oldinga(X_xor)
H = kesh["A1"]

# chiqish qatlami - shunchaki bitta chiziq
z = H @ t.W[1] + t.b[1]
print("chiqish qatlamining og'irliklari:", np.round(t.W[1].ravel(), 4))
print("z qiymatlari:", np.round(z.ravel(), 4))
print("z ishoralari:", (z > 0).astype(int).ravel())
print("kerakli javob:", y_xor.astype(int).ravel())
print("mos keladi:", bool(((z > 0).astype(float) == y_xor).all()))

for yashirin in [1, 2, 3, 4, 8]:
    yaxshi = 0
    for urug in range(10):
        t = Tarmoq([2, yashirin, 1], urug=urug)
        for _ in range(8000):
            _, kesh = t.oldinga(X_xor)
            dW, db = t.orqaga(y_xor, kesh)
            t.yangilash(dW, db, 0.5)
        bashorat, _ = t.oldinga(X_xor)
        if ((bashorat > 0.5).astype(float) == y_xor).all():
            yaxshi += 1
    print(f"{yashirin} yashirin neyron: 10 urug'dan {yaxshi} tasida yechildi")

for tezlik in [0.01, 0.1, 0.5, 2.0, 10.0]:
    t = Tarmoq([2, 3, 1], urug=3)
    for _ in range(5000):
        _, kesh = t.oldinga(X_xor)
        dW, db = t.orqaga(y_xor, kesh)
        t.yangilash(dW, db, tezlik)
    L = t.yoqotish(X_xor, y_xor)
    bashorat, _ = t.oldinga(X_xor)
    aniq = float(((bashorat > 0.5).astype(float) == y_xor).mean())
    print(f"tezlik = {tezlik:<6} yo'qotish = {L:>10.6f}  aniqlik = {aniq:.2f}")

class ChiziqliTarmoq(Tarmoq):
    def oldinga(self, X):
        A = X
        kesh = {"A0": X}
        for i in range(self.qatlamlar):
            Z = A @ self.W[i] + self.b[i]
            A = sigmoid(Z) if i == self.qatlamlar - 1 else Z   # faollashtirish YO'Q
            kesh[f"Z{i+1}"] = Z
            kesh[f"A{i+1}"] = A
        return A, kesh

    def orqaga(self, y, kesh):
        n = len(y)
        dW = [None] * self.qatlamlar
        db = [None] * self.qatlamlar
        dZ = (kesh[f"A{self.qatlamlar}"] - y) / n
        for i in range(self.qatlamlar - 1, -1, -1):
            dW[i] = kesh[f"A{i}"].T @ dZ
            db[i] = dZ.sum(axis=0)
            if i > 0:
                dZ = dZ @ self.W[i].T          # hosila = 1
        return dW, db


t = ChiziqliTarmoq([2, 8, 8, 1], urug=3)
for _ in range(20000):
    _, kesh = t.oldinga(X_xor)
    dW, db = t.orqaga(y_xor, kesh)
    t.yangilash(dW, db, 0.5)

bashorat, _ = t.oldinga(X_xor)
print("uchta qatlam, chiziqsizliksiz:")
print("  yo'qotish:", round(t.yoqotish(X_xor, y_xor), 6))
print("  bashoratlar:", np.round(bashorat.ravel(), 4))
print("  aniqlik:", float(((bashorat > 0.5).astype(float) == y_xor).mean()))