Lab for Neural Network Fundamentals.ipynb

Kernel: Python 3 (ipykernel)

Lab Exercise: Neural Network for Sequence Generation

Objective:build and train simple neural networks to model two different functions:

• Linear: y = 2 * X (50 random data points)

• Non-linear: y = X² (100 random data points)

import numpy as np
import tensorflow as tf
import matplotlib.pyplot as plt

# Set random seed for reproducibility
np.random.seed(42)
tf.random.set_seed(42)

# Function 1: y = 2 * X (Linear)
X1 = np.random.rand(50) * 10  # Random X values between 0 and 10
y1 = 2 * X1

# Function 2: y = X^2 (Non-linear)
X2 = np.random.rand(100) * 10
y2 = X2 ** 2

# Reshape input for Keras (expects 2D input)
X1 = X1.reshape(-1, 1)
y1 = y1.reshape(-1, 1)
X2 = X2.reshape(-1, 1)
y2 = y2.reshape(-1, 1)

Model 1: Linear Relationship (y = 2X)

model1 = tf.keras.Sequential([
    tf.keras.layers.Dense(1, input_shape=[1])
])

model1.compile(optimizer='adam', loss='mean_squared_error')
model1.fit(X1, y1, epochs=100, verbose=0)

# Prediction and plot
y1_pred = model1.predict(X1)

plt.scatter(X1, y1, label='Actual')
plt.plot(X1, y1_pred, color='red', label='Predicted')
plt.title('Model 1: y = 2X')
plt.xlabel('X')
plt.ylabel('y')
plt.legend()
plt.show()

C:\Users\Suyashi144893\AppData\Local\anaconda3\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)

2/2 ━━━━━━━━━━━━━━━━━━━━ 0s 27ms/step

Model 2: Non-Linear Relationship (y = X²)

model2 = tf.keras.Sequential([
    tf.keras.layers.Dense(10, activation='relu', input_shape=[1]),
    tf.keras.layers.Dense(10, activation='relu'),
    tf.keras.layers.Dense(1)
])

model2.compile(optimizer='adam', loss='mean_squared_error')
model2.fit(X2, y2, epochs=200, verbose=0)

# Prediction and plot
y2_pred = model2.predict(X2)

plt.scatter(X2, y2, label='Actual')
plt.scatter(X2, y2_pred, color='red', label='Predicted', alpha=0.5)
plt.title('Model 2: y = X²')
plt.xlabel('X')
plt.ylabel('y')
plt.legend()
plt.show()

4/4 ━━━━━━━━━━━━━━━━━━━━ 0s 13ms/step