PyTorch is a popular open-source machine learning library developed by Facebook, widely used for deep learning and research.

Why Use PyTorch?
Dynamic computation graph (eager execution)
Easy to debug and experiment with
Strong GPU acceleration (via CUDA)
Deep integration with Python ecosystem
Huge support in academia and production

Installation
bash
pip install torch torchvision torchaudio


Basic Example: Simple Neural Network
python
import torch
import torch.nn as nn
import torch.optim as optim

Dummy input/output
X = torch.randn(10, 3)
y = torch.randn(10, 1)

Define model
model = nn.Linear(3, 1)
loss_fn = nn.MSELoss()
optimizer = optim.SGD(model.parameters(), lr=0.01)

Train loop
for epoch in range(100):
y_pred = model(X)
loss = loss_fn(y_pred, y)
optimizer.zero_grad()
loss.backward()
optimizer.step()


Common Use Cases
Image classification
Natural Language Processing (NLP)
Generative models (GANs, VAEs)
Reinforcement Learning


TensorFlow, developed by Google, is a powerful framework for building and deploying machine learning models at scale.

Why Use TensorFlow?
High performance on large-scale ML tasks
Built-in support for production deployment
TensorBoard for visualization
Compatible with Keras (high-level API)
Extensive community & resources

Installation
bash
pip install tensorflow


Basic Example (Using Keras API)
python
import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import layers

Define model
model = keras.Sequential([
layers.Dense(64, activation='relu'),
layers.Dense(1)
])

Compile model
model.compile(optimizer='adam', loss='mse')

Dummy data
X = tf.random.normal((10, 3))
y = tf.random.normal((10, 1))

Train model
model.fit(X, y, epochs=10)


Common Use Cases
Deep learning at scale
Mobile/Edge deployment (TF Lite)
Time series, NLP, Computer Vision
Model serving (TF Serving)