liveBook · Manning

LeNet

LeNet is an early convolutional neural-network architecture designed primarily for handwritten-digit and character recognition.

How 3 Manning books explain it

Math and Architectures of Deep Learning

A convolutional neural network architecture introduced for digit recognition and used here as the example image classifier.

How it is used
Uses a compact convolutional architecture to classify handwritten MNIST digits.
How deep it goes
Explains layer dimensions, pooling, nonlinear activation, and implementation, but stops short of detailed optimization internals.
Examples
Uses MNIST digit images, LeNet layer dimensions, PyTorch Lightning modules, training, and inference as concrete examples.
What you can do after
Build and train a LeNet digit classifier with PyTorch Lightning, then run inference on a test batch.

Read how Math and Architectures of Deep Learning explains LeNet →

Distributed Machine Learning Patterns

LeNet is a convolutional neural network architecture originally designed for handwritten-digit recognition.

How it is used
Uses a compact CNN architecture to classify image-like video frames into selected entities.
How deep it goes
Explains the two-part architecture and input processing, but stops short of layer-specific dimensions or training procedures.
Examples
Uses handwritten-digit recognition and 28 × 28 video frames classified into ten selected entities.
What you can do after
Evaluate/understand a compact CNN architecture for image and frame classification.

Read how Distributed Machine Learning Patterns explains LeNet →

Machine Learning Algorithms in Depth

LeNet is a convolutional neural network architecture designed for visual recognition tasks.

How it is used
Classifies handwritten MNIST digits with a convolutional neural network.
How deep it goes
Explains the layer sequence, training workflow, callbacks, evaluation, and monitoring, but does not derive convolution internals.
Examples
Uses MNIST images, an architecture diagram, training and validation curves, saved predictions, and a Keras/TensorFlow implementation.
What you can do after
Apply it via Keras/TensorFlow to train, evaluate, monitor, and save predictions from an MNIST convolutional classifier.

Read how Machine Learning Algorithms in Depth explains LeNet →

What to know first

Related concepts

Questions about LeNet

What is LeNet?

LeNet is an early convolutional neural-network architecture designed primarily for handwritten-digit and character recognition.

Which Manning books explain LeNet?

Math and Architectures of Deep Learning, Distributed Machine Learning Patterns and Machine Learning Algorithms in Depth.

What should I know before learning LeNet?

Manning books that teach LeNet usually introduce convolutional neural network first.

What is LeNet a kind of?

LeNet is a kind of convolutional neural network. A convolutional neural network is a neural-network architecture that processes structured inputs with convolutional operations, typically using learned local filters to capture patterns.

What is LeNet part of?

LeNet is part of convolutional layer. A convolutional layer is a neural-network layer that applies shared learned filters to local regions of structured input to produce feature representations.

These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.