Custom Models, Layers, and Loss Functions with TensorFlow

Colleagues, the Custom Models, Layers, and Loss Functions with TensorFlow program provide learners with more control over their model architecture and tools that help them create and train advanced ML models. Gain high-demand skills in Functional APIs, Custom Layers, Custom and Exotic Models with Functional APIs and Custom Loss Functions. Compare Functional and Sequential APIs, discover new models you can build with the Functional API, and build a model that produces multiple outputs including a Siamese network, Build custom loss functions (including the contrastive loss function used in a Siamese network) in order to measure how well a model is doing and help your neural network learn from training data, Build off of existing standard layers to create custom layers for your models, customize a network layer with a lambda layer, understand the differences between them, learn what makes up a custom layer, and explore activation functions, and Build off of existing models to add custom functionality, learn how to define your own custom class instead of using the Functional or Sequential APIs, build models that can be inherited from the TensorFlow Model class, and build a residual network (ResNet) through defining a custom model class. Training modules include: 1) Functional APIs - Compare how the Functional API differs from the Sequential API, and see how the Functional API gives you additional flexibility in designing models. Practice using the functional API and build a Siamese network, 2) Custom Loss Functions - measure how well a model is doing, and are used to help a neural network learn from the training data. Learn how to build custom loss functions, including the contrastive loss function that is used in a Siamese network, 3) Custom Layers - flexibility to implement models that use non-standard layers. Practice building off of existing standard layers to create custom layers for your models, 4) Custom Models - build off of existing models to add custom functionality. This week, extend the TensorFlow Model Class to build a ResNet model, and 5) Bonus Content - customize what your model outputs or how it behaves during training and implement a custom callback to stop training once the callback detects overfitting.

Enroll today (individuals & teams welcome): https://tinyurl.com/98u4wn2c 

Much career success, Lawrence E. Wilson - Artificial Intelligence Academy