Topics for Exam 1
Topics for Exam 1
From Textbook:
  • Neural Network Design (2nd Edition),Martin T. Hagan Chapter 4 (Excluding Proof of convergence).
  • Neural Network Design (2nd Edition),Martin T. Hagan Chapter 8 (pages 8-1 to 8-12).
  • Neural Network Design (2nd Edition),Martin T. Hagan Chapter 9 (pages 9-1 to 9-10)
What you need to know (General background).
  • Python
  • Numpy:
    •  general concepts and functions (covered in numpy tutorial)
  • Vector and Matrix operations
  • Operations involving vectors and matrices
  • Solving linear equations
  • Understanding equations of lines and planes in multi-dimensional space (hyperplanes)
    
What you need to know (Textbook)
  • Neuron Model and Network Architectures
    • Single Neuron
    • Activation functions
    • Layer of Neurons
    • Weight Matrixeb
    • Biases
  • Perceptron
    • Perceptron architecture
    • Decision boundary and its relation to hyperplanes
    • Multiple neuron Perceptron
  • Performance Surfaces and Optimum Points
    • Gradient and Hessian
    • Taylor Series
    • Directional Derivatives
    • Minima and maxima
    • Sufficient and necessary conditions for optimality
  • Performance Optimization
    • Steepest Descent
    • Minimizing along a line
What you need to know (supplementary).
  • Understanding Computational Graphs and their forward and backward passes
  • Loss functions: MSE, MAE, Hinge, and Cross-entropy
  • TenosorFlow:
    • Creating and manipulating tensors
    • Creating multi-layer neural Networks
    • Calculation of outputs, errors, and gradients
    • Training and adjusting weights using the “GradientTape”
    • Performance measures
  • Keras:
    • Creating multi-layer neural Networks
    • Calculation of outputs and gradients
    • Training and adjusting weights
    • Understanding different loss functions.
    • Setting the loss function for each layer
    • Understanding the metrics for the neural networks
    • Compiling, training,  and evaluating a neural network
  • Convolutional Neural Networks (CNN):
    • Understanding convolutional filters, padding, and stride.
    • Creating convolutional, pooling, flattening, and fully connected layers
    • Determining the shape of the weight matrix
    • Determining the shape of the output for each layer
    • Determining the number of parameters
 
Coding.
  • There will be questions on the exam asking you to write or complete a code section either in numpy, tensorflow, and Keras realting to concepts covered in lectures or in assignments.. These questions may relate to parts and concepts in the assignments.
 
 
 
 
Top