from sklearn.

datasets import load_iris

from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import Perceptron
from sklearn.metrics import accuracy_score

# Load the Iris dataset

iris = load_iris()
X = iris.data
y = iris.target

# Split the data into training and testing sets

X_train, X_test, y_train, y_test = train_test_split(X, y,
test_size=0.3, random_state=1)

# Standardize the features

sc = StandardScaler()
X_train_std = sc.fit_transform(X_train)
X_test_std = sc.transform(X_test)

# Train the Perceptron model

ppn = Perceptron(max_iter=40, eta0=0.1, random_state=1)
ppn.fit(X_train_std, y_train)

# Predict the test set results

y_pred = ppn.predict(X_test_std)

# Evaluate the accuracy

print(f'Accuracy: {accuracy_score(y_test, y_pred):.2f}')

Accuracy: 0.87

import numpy as np
import matplotlib.pyplot as plt

# Sigmoid function
def sigmoid(x):
return 1 / (1 + np.exp(-x))

# Tanh function
def tanh(x):
return np.tanh(x)

# ReLU function
def relu(x):
return np.maximum(0, x)

# Leaky ReLU function

def leaky_relu(x, alpha=0.01):
return np.where(x > 0, x, x * alpha)
# Plotting the activation functions
x = np.linspace(-10, 10, 100)

plt.figure(figsize=(10, 8))
plt.plot(x, sigmoid(x), label='Sigmoid')
plt.plot(x, tanh(x), label='Tanh')
plt.plot(x, relu(x), label='ReLU')
plt.plot(x, leaky_relu(x), label='Leaky ReLU')
plt.title('Activation Functions')
plt.legend()
plt.grid(True)
plt.show()

import tensorflow as tf
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense
from sklearn.datasets import make_classification
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler

# Generate a binary classification dataset

X, y = make_classification(n_samples=1000, n_features=20, n_classes=2,
random_state=1)

# Split the data into training and testing sets

X_train, X_test, y_train, y_test = train_test_split(X, y,
test_size=0.3, random_state=1)

# Standardize the features

sc = StandardScaler()
X_train = sc.fit_transform(X_train)
X_test = sc.transform(X_test)

# Build the neural network model

model = Sequential([
Dense(64, input_dim=20, activation='relu'),
Dense(64, activation='relu'),
Dense(1, activation='sigmoid')
])

# Compile the model

model.compile(optimizer='adam', loss='binary_crossentropy',
metrics=['accuracy'])

# Train the model

model.fit(X_train, y_train, epochs=100, batch_size=10, verbose=1)

# Evaluate the model

loss, accuracy = model.evaluate(X_test, y_test, verbose=0)
print(f'Test Accuracy: {accuracy:.2f}')

D:\DLLL\DLL\Lib\site-packages\keras\src\layers\core\dense.py:87:
UserWarning: Do not pass an `input_shape`/`input_dim` argument to a
layer. When using Sequential models, prefer using an `Input(shape)`
object as the first layer in the model instead.
super().__init__(activity_regularizer=activity_regularizer,
**kwargs)

Epoch 1/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - accuracy: 0.6569 - loss:
0.6405
Epoch 2/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8191 - loss:
0.4395
Epoch 3/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8473 - loss:
0.3610
Epoch 4/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8700 - loss:
0.2950
Epoch 5/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8967 - loss:
0.2586
Epoch 6/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8922 - loss:
0.2791
Epoch 7/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8928 - loss:
0.2515
Epoch 8/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - accuracy: 0.8985 - loss:
0.2550
Epoch 9/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9081 - loss:
0.2352
Epoch 10/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9310 - loss:
0.2097
Epoch 11/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9373 - loss:
0.1976
Epoch 12/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - accuracy: 0.9322 - loss:
0.1954
Epoch 13/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9413 - loss:
0.1761
Epoch 14/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9303 - loss:
0.1954
Epoch 15/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9541 - loss:
0.1506
Epoch 16/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.9446 - loss:
0.1719
Epoch 17/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9468 - loss:
0.1678
Epoch 18/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - accuracy: 0.9549 - loss:
0.1652
Epoch 19/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9589 - loss:
0.1474
Epoch 20/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9499 - loss:
0.1471
Epoch 21/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9697 - loss:
0.1297
Epoch 22/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9748 - loss:
0.1237
Epoch 23/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9768 - loss:
0.1087
Epoch 24/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9764 - loss:
0.1181
Epoch 25/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9757 - loss:
0.0978
Epoch 26/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9780 - loss:
0.0940
Epoch 27/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9864 - loss:
0.0815
Epoch 28/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9871 - loss:
0.0804
Epoch 29/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9882 - loss:
0.0678
Epoch 30/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9920 - loss:
0.0571
Epoch 31/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9943 - loss:
0.0519
Epoch 32/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9952 - loss:
0.0489
Epoch 33/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9915 - loss:
0.0441
Epoch 34/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9944 - loss:
0.0420
Epoch 35/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9948 - loss:
0.0306
Epoch 36/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9984 - loss:
0.0334
Epoch 37/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9988 - loss:
0.0282
Epoch 38/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9969 - loss:
0.0252
Epoch 39/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9988 - loss:
0.0245
Epoch 40/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 1.0000 - loss:
0.0184
Epoch 41/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 1.0000 - loss:
0.0154
Epoch 42/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 1.0000 - loss:
0.0140
Epoch 43/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 1.0000 - loss:
0.0156
Epoch 44/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 1.0000 - loss:
0.0129
Epoch 45/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 1.0000 - loss:
0.0119
Epoch 46/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 1.0000 - loss:
0.0091
Epoch 47/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 1.0000 - loss:
0.0098
Epoch 48/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 1.0000 - loss:
0.0100
Epoch 49/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 1.0000 - loss:
0.0079
Epoch 50/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - accuracy: 1.0000 - loss:
0.0085
Epoch 51/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 1.0000 - loss:
0.0061
Epoch 52/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 1.0000 - loss:
0.0060
Epoch 53/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 1.0000 - loss:
0.0056
Epoch 54/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 1.0000 - loss:
0.0054
Epoch 55/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 1.0000 - loss:
0.0050
Epoch 56/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 1.0000 - loss:
0.0040
Epoch 57/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 1.0000 - loss:
0.0044
Epoch 58/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 1.0000 - loss:
0.0039
Epoch 59/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 1.0000 - loss:
0.0037
Epoch 60/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 1.0000 - loss:
0.0034
Epoch 61/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 1.0000 - loss:
0.0034
Epoch 62/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 1.0000 - loss:
0.0033
Epoch 63/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 1.0000 - loss:
0.0029
Epoch 64/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 1.0000 - loss:
0.0029
Epoch 65/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 1.0000 - loss:
0.0026
Epoch 66/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 1.0000 - loss:
0.0021
Epoch 67/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 1.0000 - loss:
0.0021
Epoch 68/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 1.0000 - loss:
0.0018
Epoch 69/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 1.0000 - loss:
0.0016
Epoch 70/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 1.0000 - loss:
0.0017
Epoch 71/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 1.0000 - loss:
0.0016
Epoch 72/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 1.0000 - loss:
0.0016
Epoch 73/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - accuracy: 1.0000 - loss:
0.0014
Epoch 74/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 1.0000 - loss:
0.0014
Epoch 75/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 1.0000 - loss:
0.0012
Epoch 76/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 1.0000 - loss:
0.0013
Epoch 77/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 1.0000 - loss:
0.0011
Epoch 78/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 1.0000 - loss:
0.0011
Epoch 79/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 1.0000 - loss:
9.9367e-04
Epoch 80/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 1.0000 - loss:
9.3148e-04
Epoch 81/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 1.0000 - loss:
9.9012e-04
Epoch 82/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 1.0000 - loss:
8.2529e-04
Epoch 83/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 1.0000 - loss:
9.2186e-04
Epoch 84/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 1.0000 - loss:
8.1299e-04
Epoch 85/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 1.0000 - loss:
8.0663e-04
Epoch 86/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 1.0000 - loss:
7.7992e-04
Epoch 87/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 1.0000 - loss:
6.0982e-04
Epoch 88/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 1.0000 - loss:
5.8337e-04
Epoch 89/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 1.0000 - loss:
6.2005e-04
Epoch 90/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 1.0000 - loss:
5.8850e-04
Epoch 91/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 4ms/step - accuracy: 1.0000 - loss:
5.3105e-04
Epoch 92/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - accuracy: 1.0000 - loss:
5.2282e-04
Epoch 93/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - accuracy: 1.0000 - loss:
4.5882e-04
Epoch 94/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - accuracy: 1.0000 - loss:
4.8520e-04
Epoch 95/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 1.0000 - loss:
4.2262e-04
Epoch 96/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - accuracy: 1.0000 - loss:
4.1262e-04
Epoch 97/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - accuracy: 1.0000 - loss:
3.7000e-04
Epoch 98/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - accuracy: 1.0000 - loss:
3.8988e-04
Epoch 99/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - accuracy: 1.0000 - loss:
3.9310e-04
Epoch 100/100
70/70 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - accuracy: 1.0000 - loss:
3.2804e-04
Test Accuracy: 0.80

import tensorflow as tf
from tensorflow.keras.datasets import imdb
from tensorflow.keras.preprocessing.sequence import pad_sequences
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Embedding, GRU, LSTM, Dense

# Load the IMDB dataset

max_features = 10000
maxlen = 500
(x_train, y_train), (x_test, y_test) =
imdb.load_data(num_words=max_features)

# Pad sequences to ensure uniform length

x_train = pad_sequences(x_train, maxlen=maxlen)
x_test = pad_sequences(x_test, maxlen=maxlen)

# Build the GRU model

gru_model = Sequential([
Embedding(max_features, 128, input_length=maxlen),
GRU(128, return_sequences=True),
GRU(128),
Dense(1, activation='sigmoid')
])

# Compile the model

gru_model.compile(optimizer='adam', loss='binary_crossentropy',
metrics=['accuracy'])

# Train the GRU model

gru_model.fit(x_train, y_train, epochs=10, batch_size=32,
validation_split=0.2)

# Evaluate the GRU model

gru_loss, gru_accuracy = gru_model.evaluate(x_test, y_test)
print(f'GRU Test Accuracy: {gru_accuracy:.2f}')

# Build the LSTM model

lstm_model = Sequential([
Embedding(max_features, 128, input_length=maxlen),
LSTM(128, return_sequences=True),
LSTM(128),
Dense(1, activation='sigmoid')
])

# Compile the model

lstm_model.compile(optimizer='adam', loss='binary_crossentropy',
metrics=['accuracy'])

# Train the LSTM model

lstm_model.fit(x_train, y_train, epochs=10, batch_size=32,
validation_split=0.2)

# Evaluate the LSTM model

lstm_loss, lstm_accuracy = lstm_model.evaluate(x_test, y_test)
print(f'LSTM Test Accuracy: {lstm_accuracy:.2f}')

Downloading data from https://storage.googleapis.com/tensorflow/tf-

keras-datasets/imdb.npz
17464789/17464789 ━━━━━━━━━━━━━━━━━━━━ 5s 0us/step
Epoch 1/10

D:\DLLL\DLL\Lib\site-packages\keras\src\layers\core\embedding.py:90:
UserWarning: Argument `input_length` is deprecated. Just remove it.
warnings.warn(

625/625 ━━━━━━━━━━━━━━━━━━━━ 426s 675ms/step - accuracy: 0.6963 -

loss: 0.5475 - val_accuracy: 0.8776 - val_loss: 0.2865
Epoch 2/10
625/625 ━━━━━━━━━━━━━━━━━━━━ 361s 577ms/step - accuracy: 0.9234 -
loss: 0.1987 - val_accuracy: 0.8986 - val_loss: 0.2472
Epoch 3/10
625/625 ━━━━━━━━━━━━━━━━━━━━ 370s 592ms/step - accuracy: 0.9599 -
loss: 0.1109 - val_accuracy: 0.8862 - val_loss: 0.3061
Epoch 4/10
625/625 ━━━━━━━━━━━━━━━━━━━━ 365s 585ms/step - accuracy: 0.9780 -
loss: 0.0649 - val_accuracy: 0.8800 - val_loss: 0.3690
Epoch 5/10
625/625 ━━━━━━━━━━━━━━━━━━━━ 1268s 2s/step - accuracy: 0.9897 - loss:
0.0346 - val_accuracy: 0.8772 - val_loss: 0.4095
Epoch 6/10
625/625 ━━━━━━━━━━━━━━━━━━━━ 388s 621ms/step - accuracy: 0.9928 -
loss: 0.0203 - val_accuracy: 0.8798 - val_loss: 0.5286
Epoch 7/10
625/625 ━━━━━━━━━━━━━━━━━━━━ 478s 679ms/step - accuracy: 0.9945 -
loss: 0.0164 - val_accuracy: 0.8770 - val_loss: 0.6116
Epoch 8/10
625/625 ━━━━━━━━━━━━━━━━━━━━ 549s 877ms/step - accuracy: 0.9942 -
loss: 0.0172 - val_accuracy: 0.8726 - val_loss: 0.6035
Epoch 9/10
625/625 ━━━━━━━━━━━━━━━━━━━━ 413s 661ms/step - accuracy: 0.9956 -
loss: 0.0130 - val_accuracy: 0.8828 - val_loss: 0.6268
Epoch 10/10
625/625 ━━━━━━━━━━━━━━━━━━━━ 405s 648ms/step - accuracy: 0.9967 -
loss: 0.0075 - val_accuracy: 0.8780 - val_loss: 0.6703
782/782 ━━━━━━━━━━━━━━━━━━━━ 134s 171ms/step - accuracy: 0.8635 -
loss: 0.7443
GRU Test Accuracy: 0.87
Epoch 1/10
625/625 ━━━━━━━━━━━━━━━━━━━━ 431s 684ms/step - accuracy: 0.7186 -
loss: 0.5298 - val_accuracy: 0.8610 - val_loss: 0.3262
Epoch 2/10
625/625 ━━━━━━━━━━━━━━━━━━━━ 448s 718ms/step - accuracy: 0.8893 -
loss: 0.2852 - val_accuracy: 0.7778 - val_loss: 0.4798
Epoch 3/10
625/625 ━━━━━━━━━━━━━━━━━━━━ 449s 719ms/step - accuracy: 0.8647 -
loss: 0.3316 - val_accuracy: 0.6588 - val_loss: 0.6006
Epoch 4/10
625/625 ━━━━━━━━━━━━━━━━━━━━ 466s 746ms/step - accuracy: 0.8898 -
loss: 0.2702 - val_accuracy: 0.8588 - val_loss: 0.3653
Epoch 5/10
625/625 ━━━━━━━━━━━━━━━━━━━━ 687s 1s/step - accuracy: 0.9489 - loss:
0.1414 - val_accuracy: 0.8678 - val_loss: 0.3932
Epoch 6/10
625/625 ━━━━━━━━━━━━━━━━━━━━ 790s 1s/step - accuracy: 0.9633 - loss:
0.1045 - val_accuracy: 0.8536 - val_loss: 0.4131
Epoch 7/10
625/625 ━━━━━━━━━━━━━━━━━━━━ 748s 1s/step - accuracy: 0.9642 - loss:
0.1008 - val_accuracy: 0.8598 - val_loss: 0.4098
Epoch 8/10
625/625 ━━━━━━━━━━━━━━━━━━━━ 738s 1s/step - accuracy: 0.9696 - loss:
0.0897 - val_accuracy: 0.8656 - val_loss: 0.4937
Epoch 9/10
625/625 ━━━━━━━━━━━━━━━━━━━━ 770s 1s/step - accuracy: 0.9859 - loss:
0.0480 - val_accuracy: 0.8578 - val_loss: 0.4825
Epoch 10/10
625/625 ━━━━━━━━━━━━━━━━━━━━ 754s 1s/step - accuracy: 0.9857 - loss:
0.0457 - val_accuracy: 0.8462 - val_loss: 0.5925
782/782 ━━━━━━━━━━━━━━━━━━━━ 319s 408ms/step - accuracy: 0.8414 -
loss: 0.6129
LSTM Test Accuracy: 0.84

from tensorflow.keras.datasets import reuters

from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Dropout, Activation
from tensorflow.keras.preprocessing.text import Tokenizer
from tensorflow.keras.utils import to_categorical

# Load the Reuters dataset

max_words = 10000
(x_train, y_train), (x_test, y_test) =
reuters.load_data(num_words=max_words)

# Tokenize and prepare the data

tokenizer = Tokenizer(num_words=max_words)
x_train = tokenizer.sequences_to_matrix(x_train, mode='binary')
x_test = tokenizer.sequences_to_matrix(x_test, mode='binary')

# Convert labels to categorical format

y_train = to_categorical(y_train)
y_test = to_categorical(y_test)

# Build the model

model = Sequential([
 Dense(512, input_shape=(max_words,), activation='relu'),
Dropout(0.5),
Dense(512, activation='relu'),
Dropout(0.5),
Dense(46, activation='softmax')
])

# Compile the model

model.compile(optimizer='adam', loss='categorical_crossentropy',
metrics=['accuracy'])

# Train the model

model.fit(x_train, y_train, epochs=5, batch_size=32,
validation_split=0.2)

# Evaluate the model

score = model.evaluate(x_test, y_test, batch_size=32)
print(f'Test Accuracy: {score[1]:.2f}')

Downloading data from https://storage.googleapis.com/tensorflow/tf-

keras-datasets/reuters.npz
2110848/2110848 ━━━━━━━━━━━━━━━━━━━━ 2s 1us/step
Epoch 1/5
225/225 ━━━━━━━━━━━━━━━━━━━━ 21s 63ms/step - accuracy: 0.5543 - loss:
1.9647 - val_accuracy: 0.7657 - val_loss: 1.0688
Epoch 2/5
225/225 ━━━━━━━━━━━━━━━━━━━━ 14s 61ms/step - accuracy: 0.8114 - loss:
0.8275 - val_accuracy: 0.7974 - val_loss: 0.9105
Epoch 3/5
225/225 ━━━━━━━━━━━━━━━━━━━━ 14s 61ms/step - accuracy: 0.8856 - loss:
0.4954 - val_accuracy: 0.8102 - val_loss: 0.8875
Epoch 4/5
225/225 ━━━━━━━━━━━━━━━━━━━━ 14s 60ms/step - accuracy: 0.9202 - loss:
0.3315 - val_accuracy: 0.8180 - val_loss: 0.9512
Epoch 5/5
225/225 ━━━━━━━━━━━━━━━━━━━━ 14s 60ms/step - accuracy: 0.9420 - loss:
0.2663 - val_accuracy: 0.8147 - val_loss: 0.9796
71/71 ━━━━━━━━━━━━━━━━━━━━ 1s 11ms/step - accuracy: 0.8156 - loss:
1.0390
Test Accuracy: 0.81

import tensorflow as tf
from tensorflow.keras.datasets import mnist
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Conv2D, MaxPooling2D, Flatten,
Dense, Dropout
from tensorflow.keras.utils import to_categorical

# Load the MNIST dataset

(x_train, y_train), (x_test, y_test) = mnist.load_data()
# Reshape and normalize the data
x_train = x_train.reshape(x_train.shape[0], 28, 28,
1).astype('float32') / 255
x_test = x_test.reshape(x_test.shape[0], 28, 28, 1).astype('float32')
/ 255

# Convert labels to categorical format

y_train = to_categorical(y_train, 10)
y_test = to_categorical(y_test, 10)

# Build the CNN model

model = Sequential([
Conv2D(32, kernel_size=(3, 3), activation='relu', input_shape=(28,
28, 1)),
MaxPooling2D(pool_size=(2, 2)),
Conv2D(64, kernel_size=(3, 3), activation='relu'),
MaxPooling2D(pool_size=(2, 2)),
Flatten(),
Dense(128, activation='relu'),
Dropout(0.5),
Dense(10, activation='softmax')
])

# Compile the model

model.compile(optimizer='adam', loss='categorical_crossentropy',
metrics=['accuracy'])

# Train the model

model.fit(x_train, y_train, epochs=10, batch_size=128,
validation_split=0.2)

# Evaluate the model

test_loss, test_acc = model.evaluate(x_test, y_test)
print(f'Test Accuracy: {test_acc:.2f}')

Downloading data from https://storage.googleapis.com/tensorflow/tf-

keras-datasets/mnist.npz
11490434/11490434 ━━━━━━━━━━━━━━━━━━━━ 2s 0us/step

D:\DLLL\DLL\Lib\site-packages\keras\src\layers\convolutional\
base_conv.py:107: UserWarning: Do not pass an
`input_shape`/`input_dim` argument to a layer. When using Sequential
models, prefer using an `Input(shape)` object as the first layer in
the model instead.
super().__init__(activity_regularizer=activity_regularizer,
**kwargs)

Epoch 1/10
375/375 ━━━━━━━━━━━━━━━━━━━━ 24s 56ms/step - accuracy: 0.7800 - loss:
0.7019 - val_accuracy: 0.9766 - val_loss: 0.0779
Epoch 2/10
375/375 ━━━━━━━━━━━━━━━━━━━━ 20s 54ms/step - accuracy: 0.9629 - loss:
0.1246 - val_accuracy: 0.9837 - val_loss: 0.0572
Epoch 3/10
375/375 ━━━━━━━━━━━━━━━━━━━━ 21s 55ms/step - accuracy: 0.9757 - loss:
0.0824 - val_accuracy: 0.9862 - val_loss: 0.0489
Epoch 4/10
375/375 ━━━━━━━━━━━━━━━━━━━━ 21s 55ms/step - accuracy: 0.9792 - loss:
0.0705 - val_accuracy: 0.9872 - val_loss: 0.0443
Epoch 5/10
375/375 ━━━━━━━━━━━━━━━━━━━━ 20s 54ms/step - accuracy: 0.9823 - loss:
0.0555 - val_accuracy: 0.9887 - val_loss: 0.0403
Epoch 6/10
375/375 ━━━━━━━━━━━━━━━━━━━━ 20s 54ms/step - accuracy: 0.9860 - loss:
0.0477 - val_accuracy: 0.9876 - val_loss: 0.0420
Epoch 7/10
375/375 ━━━━━━━━━━━━━━━━━━━━ 20s 53ms/step - accuracy: 0.9866 - loss:
0.0444 - val_accuracy: 0.9898 - val_loss: 0.0371
Epoch 8/10
375/375 ━━━━━━━━━━━━━━━━━━━━ 21s 54ms/step - accuracy: 0.9871 - loss:
0.0394 - val_accuracy: 0.9902 - val_loss: 0.0360
Epoch 9/10
375/375 ━━━━━━━━━━━━━━━━━━━━ 26s 68ms/step - accuracy: 0.9913 - loss:
0.0298 - val_accuracy: 0.9911 - val_loss: 0.0347
Epoch 10/10
375/375 ━━━━━━━━━━━━━━━━━━━━ 20s 54ms/step - accuracy: 0.9896 - loss:
0.0308 - val_accuracy: 0.9905 - val_loss: 0.0356
313/313 ━━━━━━━━━━━━━━━━━━━━ 3s 8ms/step - accuracy: 0.9897 - loss:
0.0311
Test Accuracy: 0.99

import tensorflow as tf
from tensorflow.keras.datasets import imdb
from tensorflow.keras.preprocessing.sequence import pad_sequences
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Embedding, SimpleRNN, Dense

# Load the IMDB dataset

max_features = 10000
maxlen = 500
(x_train, y_train), (x_test, y_test) =
imdb.load_data(num_words=max_features)

# Pad sequences to ensure uniform length

x_train = pad_sequences(x_train, maxlen=maxlen)
x_test = pad_sequences(x_test, maxlen=maxlen)

# Build the Simple RNN model

model = Sequential([
Embedding(max_features, 128, input_length=maxlen),
 SimpleRNN(128),
Dense(1, activation='sigmoid')
])

# Compile the model

model.compile(optimizer='adam', loss='binary_crossentropy',
metrics=['accuracy'])

# Train the model

model.fit(x_train, y_train, epochs=3, batch_size=32,
validation_split=0.2)

# Evaluate the model

test_loss, test_acc = model.evaluate(x_test, y_test)
print(f'Test Accuracy: {test_acc:.2f}')

Epoch 1/3
625/625 ━━━━━━━━━━━━━━━━━━━━ 62s 95ms/step - accuracy: 0.5335 - loss:
0.6886 - val_accuracy: 0.5994 - val_loss: 0.6500
Epoch 2/3
625/625 ━━━━━━━━━━━━━━━━━━━━ 80s 91ms/step - accuracy: 0.6730 - loss:
0.6060 - val_accuracy: 0.6544 - val_loss: 0.6207
Epoch 3/3
625/625 ━━━━━━━━━━━━━━━━━━━━ 63s 100ms/step - accuracy: 0.7287 - loss:
0.5338 - val_accuracy: 0.6736 - val_loss: 0.6298
782/782 ━━━━━━━━━━━━━━━━━━━━ 24s 31ms/step - accuracy: 0.6723 - loss:
0.6265
Test Accuracy: 0.67