BCS405C |OPTIMIZATION TECHNIQUE

Module 1
Functions of several variables, Differentiation and partial differentials, gradients of
vector-valued functions, gradients of matrices, useful identities for computing gradients,
linearization and multivariate Taylor series
Module 2
Backpropagation and automatic differentiation, gradients in a deep network, The Gradient of Quadratic Cost, Descending the Gradient of Cost, The Gradient of Mean Squared Error.
Module 3
Local and global optima, convex sets and functions separating hyperplanes, application of Hessian matrix in optimization, Optimization using gradient descent, Sequential search 3- point search and Fibonacci search.
Module 4
Unconstrained optimization -Method of steepest ascent/descent, NR method, Gradient descent, Mini batch gradient descent, Stochastic gradient descent.
Module 5
Momentum-based gradient descent methods: Adagrad, RMSprop and Adam. Non-Convex Optimization: Convergence to Critical Points, Saddle-Point methods.

BCS405C | Model Question Paper with Solution

MQP Solution
Access well‑organized Model Question Paper with step‑by‑step, point‑wise solutions. Each solution is created to save your time, clarify concepts, and help you revise effectively. 

BCS405C | Passing Package
( Score More )

Passing Package
A smart package made for VTU students! Selected important questions prepared to cover exactly what matters in VTU exams. Clear, simple, and quick to revise – perfect for last‑minute preparation and aiming for better marks with confidence.