Knowledge Hub
A collection of technical notes, concepts, tutorials, and documentation across Machine Learning, Python, research simulators, and academic workflows.
Tutorials
Step-by-step notes for LaTeX, simulation tools, channel modeling, Python, and research data analysis.
Knowledge Base
Concept notes and reference materials organized by topic.
machine learning
- Basics & ClassificationsA clearer introduction to machine learning, the basic vocabulary, and how classification problems are framed.
- Supervised, Unsupervised & Semi-SupervisedA practical guide to the main ways machines learn from labeled, unlabeled, and partly labeled data.
- Basic Parameters in ML, DL, DNN, and DRLA beginner-friendly guide to common machine learning, deep learning, DNN, and DRL parameters such as seed, batch size, epoch, bias, overfitting, underfitting, learning rate, and exploration.
- Gradient Descent AlgorithmA deeper but beginner-friendly explanation of gradient descent, learning rate, optimization variants, and common training problems.
- Classification AlgorithmsA deeper guide to common classification algorithms, their intuition, strengths, weaknesses, and practical use cases.
- Regression AlgorithmsA deeper explanation of regression models for predicting continuous values, with intuition, assumptions, and practical guidance.
- Ridge and Kernel Ridge RegressionA beginner-friendly explanation of Ridge Regression and Kernel Ridge Regression from first principles, with intuition, equations, kernels, and Python examples.
- Comparison Between Classifiers and Regressors and Their EfficiencyA practical comparison of classifiers and regressors, including output type, metrics, computational efficiency, and model-selection guidance.
- Deep Learning ArchitecturesA clearer and deeper guide to neural networks, CNNs, RNNs, transformers, training, and practical limitations.
- Reinforcement Learning & DRLA clearer and deeper guide to reinforcement learning, value functions, policies, exploration, Q-learning, and deep RL.
- Transfer LearningA practical guide to transfer learning, frozen layers, fine-tuning, applications, benefits, and limitations.
reconfigurable intelligent surface
- 1. What is a Reconfigurable Intelligent Surface (RIS)?A detailed beginner-friendly explanation of RIS, smart radio environments, and why RIS is important for 6G wireless networks.
- 2. Principles, Types, Pros & ConsA deeper explanation of RIS physics, architectures, design variables, advantages, and practical limitations.
- 3. Use Cases & ApplicationsA structured view of RIS applications in coverage, interference control, security, IoT, sensing, and smart indoor environments.
- 4. Localization PerspectiveHow RIS helps localization through virtual anchors, controllable paths, near-field wavefronts, and channel-parameter estimation.
- 5. mmWave Localization PerspectiveWhy mmWave and RIS are naturally connected for high-resolution positioning, beam training, and near-field localization.
- 6. RIS in 6G mmWave NetworksA 6G-oriented view of RIS in mmWave/sub-THz networks, including deployment, AI control, digital twins, and open research directions.
integrated sensing and communication
- 1. What is Integrated Sensing and Communication (ISAC)?A detailed introduction to ISAC, why it matters for 6G, and how a radio signal can both communicate and sense.
- 2. Principles, Waveform Design & Trade-offsThe signal-processing principles behind ISAC, including waveform design, sensing metrics, communication metrics, and unavoidable trade-offs.
- 3. Transformative Use CasesMajor ISAC use cases in autonomous mobility, smart factories, healthcare, drones, localization, and network intelligence.
- 4. Localization & Tracking PerspectiveHow ISAC supports device-based and device-free localization, tracking, Doppler estimation, and predictive beamforming.
- 5. mmWave and Terahertz ISAC PerspectiveWhy mmWave and THz frequencies are central to high-resolution ISAC, and what challenges they introduce.
- 6. ISAC-Aided 6G NetworksHow ISAC fits into 6G networks with AI, RIS, digital twins, edge computing, and sensing-as-a-service.
ris assisted isac system
- 1. How ISAC is Connected to RISWhy RIS and ISAC naturally fit together in 6G networks, and what problem each technology solves.
- 2. How Communication and Sensing is Done?The mechanics of RIS-assisted ISAC, including joint beamforming, RIS phase control, sensing echoes, and communication constraints.
- 3. How RIS Can Assist?The main ways RIS improves ISAC: blockage recovery, virtual anchors, sensing geometry, interference control, and active/multifunctional operation.
- 4. What are the Recent Trends?Recent research trends in RIS-assisted ISAC, including active RIS, STAR-RIS, NOMA, learning-based control, near-field sensing, and multifunctional surfaces.
- 5. Scopes and Future ChallengesOpen research directions for RIS-assisted ISAC, from channel estimation and beamforming to privacy, hardware, standardization, and real-world deployment.