🎓 Computer Science & Engineering Portal

Master Engineering Disciplines with Structured Notes

Comprehensive academic lecture notes, exam-oriented unit summaries, laboratory manuals, and previous year question papers designed strictly for university students.

📑

University Syllabi

AKTU & AICTE aligned semester credit guidelines.

📝

Exam Question Papers

Previous 5 years solved university semester papers.

💡

Lab Manuals & Viva

Practical codes with outputs and interview questions.

Core Subjects & Units Hub

Click on any specific unit to immediately view its lecture notes below

🎨 Computer Graphics (CG)

Scan Conversion, Bresenham Line & Circle, 2D/3D Transformations, Viewing & Clipping.

Unit 1: Raster Scan, DDA & Bresenham →
Unit 2: 2D & 3D Transformations →
Unit 3: Sutherland-Hodgman & Clipping →
Unit 4: Hidden Surface Elimination →

🧠 Machine Learning (ML / MLT)

Supervised/Unsupervised Learning, Regression, Decision Trees, SVM, Neural Nets & Clustering.

Unit 1: Linear & Logistic Regression →
Unit 2: Decision Trees & Support Vector (SVM) →
Unit 3: K-Means & Dimensionality Reduction →
Unit 4: Neural Networks & Gradient Descent →

🤖 Artificial Intelligence (AI)

Search Algorithms, First Order Logic, Probabilistic Reasoning, Expert Systems & Robotics.

Unit 1: Propositional Logic & Connectives →
Unit 2: Probabilistic Reasoning & Uncertainty →
Unit 3: State Space Search & Heuristics →
Unit 4: First Order Predicate Logic (FOL) →

🗄️ Database Management (DBMS)

ER-Modeling, Relational Algebra, SQL Queries, Normalization (1NF-BCNF) and ACID Transactions.

Unit 1: ER Model, Entities & Attributes →
Unit 2: Functional Dependencies & 1NF to BCNF →
Unit 3: ACID Properties & Concurrency Control →
Unit 4: Relational Algebra & Complex SQL Joins →

🌲 Data Structures & Algorithms

Arrays, Linked Lists, Stacks, Queues, Binary Trees, Graphs, Sorting & Asymptotic Analysis.

Unit 1: Arrays, Matrices & Recursion →
Unit 2: Stacks, Queues & Infix-to-Postfix →
Unit 3: Binary Trees, BST & AVL Rotations →
Unit 4: Graphs (BFS, DFS, Dijkstra, MST) →

⚡ Operating Systems

Process Scheduling, Deadlocks, Synchronization, Virtual Memory, Paging and Disk Management.

Unit 1: Process States, PCB & Multi-Threading →
Unit 2: CPU Scheduling (FCFS, SJF, RR) →
Unit 3: Deadlocks, Semaphores & Banker's Algo →
Unit 4: Virtual Memory, Paging & Disk Scheduling →

🌐 Computer Networks

OSI & TCP/IP Models, Error Detection, IPv4 Subnetting, Routing Protocols and TCP Handshake.

Unit 1: OSI vs TCP/IP Protocol Architectures →
Unit 2: Data Link Layer, Framing & Sliding Window →
Unit 3: IPv4 Addressing, Subnetting & Routing →
Unit 4: Transport Layer (TCP 3-Way Handshake) →

⚙️ Design of Algorithms (DAA)

Asymptotic Notations, Divide & Conquer, Dynamic Programming, Greedy Approach & Backtracking.

Unit 1: Time Complexity, Master's Theorem →
Unit 2: 0/1 Knapsack & Dynamic Programming →
Unit 3: Greedy Methods & Graph Algorithms →
Viewing All Lectures

Derivation of the Gradient Descent Rule

How to calculate the direction of steepest descent along the error surface?

The direction of steepest can be found by computing the derivative of E with respect to each component of the vector wvector . This vector derivative is called the gradient of E with respect to             wvector , written as

The gradient specifies the direction of steepest increase of E, the training rule for gradient descent is

 


  • Here η is a positive constant called the learning rate, which determines the step size in the gradient descent search.
  • The negative sign is present because we want to move the weight vector in the direction that decreases E.

This training rule can also be written in its component form 

Calculate the gradient at each step. The vector of 𝜕𝐸/𝜕𝑤𝑖 derivatives that form the gradient can be obtained by differentiating E from Equation (2), as



Labels: ,

Discussion & Queries (<$I18NNumComments$>):

<$CommentPager$>
<$I18NAtCommentTimeWithPermalink$>, <$I18NCommentAuthorSaid$>

<$BlogCommentBody$>

<$BlogCommentDeleteIcon$>
<$CommentPager$>