The presentation provides a sweeping introduction to neural networks, covering fundamental concepts from biological inspiration to mathematical implementation. Topics include an overview of network architectures, activation functions, forward propagation, Backpropagation, and training techniques. Attendees will gain a foundational understanding of how Multilayer Perceptron (MLP) and deep networks learn complex patterns from data.
– Fundamental Concepts: Introduction to artificial neurons, weights, biases, and the structure of layers (input, hidden, output)
– Network Operations: How neural networks compute outputs through forward propagation
– Learning Mechanisms: Training, loss functions, and the Backpropagation
– Non-linearity and Activation Functions: ReLU, Sigmoid, and Tanh functions
– Real-World Inferencing Applications: Sample of use-case scenarios
Speaker(s): Randy Rannow
Downtown Paninos – 604 North Tejon Street, Colorado Springs, Colorado, United States, Virtual: https://events.vtools.ieee.org/m/566622