Free video class shows how to utilize Wolfram Language’s easy-to-use framework to build, modify, train and deploy neural networks and artificial intelligence more intuitively.
Summary
This video showcases the easy-to-use framework available in the Wolfram Language to build, modify, train and deploy neural networks. Learn how the Wolfram Language simplifies the process of encoding input and decoding output for neural nets. Also introduced are layers (almost 30 different types)—the basic building blocks for constructing neural networks—and the process of connecting them in chains and graphs to build complicated networks according to your requirements. This class is intended for users who have a basic familiarity with neural nets and who would like to explore the Wolfram Language features that make the process of building and training networks more intuitive.
Featured Products & Technologies: Wolfram Language (available in Mathematica and Wolfram|One)
You'll Learn To
Feed data into networks by encoding tensors
Build network structure by connecting layers using chains and graphs
Train the network to learn from training data
Use loss functions to tune the training process
Summary
This video showcases the easy-to-use framework available in the Wolfram Language to build, modify, train and deploy neural networks. Learn how the Wolfram Language simplifies the process of encoding input and decoding output for neural nets. Also introduced are layers (almost 30 different types)—the basic building blocks for constructing neural networks—and the process of connecting them in chains and graphs to build complicated networks according to your requirements. This class is intended for users who have a basic familiarity with neural nets and who would like to explore the Wolfram Language features that make the process of building and training networks more intuitive.
Featured Products & Technologies: Wolfram Language (available in Mathematica and Wolfram|One)
You'll Learn To
Feed data into networks by encoding tensors
Build network structure by connecting layers using chains and graphs
Train the network to learn from training data
Use loss functions to tune the training process
