What libraries or tools have you used for neural network work?

In practice, the following libraries and tools are often used when working with neural networks in Python:

• TensorFlow — a powerful framework from Google for creating and training neural networks, supporting both high-level API Keras and low-level programming.
• PyTorch — a popular library from Facebook, known for its dynamic computational graph, convenient for research and prototyping.
• Keras — a high-level API for neural networks that can run on top of TensorFlow, simplifying model creation.
• scikit-learn — although not a specialized library for neural networks, it contains simple models and tools for data preprocessing.
• OpenCV — for image processing, often used together with neural networks in computer vision tasks.

Example of creating a simple neural network in Keras:

from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense

model = Sequential([
    Dense(64, activation='relu', input_shape=(100,)),
    Dense(10, activation='softmax')
])

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