Learning Loops in Programming for Efficiency

 Controlling the Light: Brightness Adjustment with NumPy! 💡🌓 Day 87/100 In Computer Vision, light isn't a feeling it's an addition. For Day 87 of my #100DaysOfCode journey, I explored the mathematics of Exposure and Brightness. I learned that making a photo 'pop' is actually a simple matter of scalar addition across a 3D matrix. But the real skill lies in Clipping ensuring the math doesn't break the boundaries of 8-bit color depth. Technical Highlights: 💡 Scalar Offsetting: Using NumPy broadcasting to shift the global intensity of an image by adding or subtracting constant values. 🛡️ Value Clipping: Implementing np.clip to prevent numerical overflows, ensuring pixels never exceed 255 or drop below 0. ⚡ Performance Vectorization: Avoiding slow Python loops and using direct array operations for real-time image manipulation. 🤖 Preprocessing for AI: Understanding how brightness normalization helps ML models recognize objects in varying lighting conditions. Do check my GitHub repository here : https://lnkd.in/d9Yi9ZsC #100DaysOfCode #ComputerVision #NumPy #Python #BTech #IILM #AIML #ImageProcessing #DataScience #SoftwareEngineering #LearningInPublic #WomenInTech

🚀 Day 48 of My Learning Journey Today, I explored two important NumPy functions: identity() and eye() 📊 🔹 identity() Creates a square matrix Main diagonal elements are 1, rest are 0 Useful for mathematical and matrix operations 🔹 eye() More flexible than identity() Can create rectangular matrices Allows shifting the diagonal using parameter k k = 0 → main diagonal k > 0 → upper diagonal k < 0 → lower diagonal 💻 Example: np.identity(3) → 3×3 identity matrix np.eye(3, 4) → 3×4 matrix with diagonal 1s ✨ Key Learning: Understanding these functions helps in working with matrices efficiently, especially in linear algebra and data science applications. 📌 Consistency is the key—small steps every day lead to big results! #Day48#Python #NumPy #LearningJourney #DataScience #Coding #StudentLife

The Magic of the Mirror: Image Flipping with NumPy! 🤳🔄 Day 85/100 Ever wondered how your phone 'mirrors' your selfies instantly? It’s just one line of array slicing! For Day 85 of my #100DaysOfCode, I explored Image Flipping and Mirroring. In the world of Computer Vision, an image is just a matrix, and to flip it, we simply reverse the order in which we read the rows or columns. Technical Highlights: 🔄 Axis Reversal: Mastering the [::-1] slicing syntax to reverse array indices without complex loops. 🤳 Mirror Logic: Implementing horizontal flips to simulate the front-camera 'selfie' experience. 🌊 Vertical Reflection: Creating water surface reflection effects by reversing the row order of 2D matrices. 🤖 AI Data Augmentation: Learning how flipping images is used in Machine Learning to double the size of training datasets and prevent model bias. Do check my GitHub repository here : https://lnkd.in/d9Yi9ZsC #100DaysOfCode #ComputerVision #NumPy #Python #BTech #IILM #AIML #ImageProcessing #DataAugmentation #SoftwareEngineering #LearningInPublic #WomenInTech

🚀 Excited to share my latest work on Machine Learning & AI Practicals! I’ve created a collection of hands-on Jupyter Notebooks covering core ML concepts and algorithms as part of my academic learning journey. This project helped me strengthen my understanding by implementing models from scratch and analyzing real datasets. 📂 Key topics covered: 🔹 DataFrame Operations 🔹 Correlation Matrix 🔹 Normal Distribution 🔹 Simple Linear Regression 🔹 Logistic Regression 🔹 Decision Trees (ID3 Algorithm) 🔹 Confusion Matrix 🔹 Decision Tree Pruning 🛠️ Tools & Technologies: Python | Pandas | NumPy | Scikit-learn | Matplotlib | Jupyter Notebook 💡 Through this project, I gained practical experience in: ✔️ Data preprocessing ✔️ Model building & evaluation ✔️ Data visualization ✔️ Understanding ML algorithms in depth 🔗 Check out my GitHub repository: https://lnkd.in/gSbCu_Aq I’m continuously learning and exploring more in the field of AI & ML. Open to feedback and suggestions! #MachineLearning #ArtificialIntelligence #DataScience #Python #LearningJourney #GitHub #Students #AI #ML

Day 19 of My AI Journey 🚀 Today I started connecting my programming fundamentals with Generative AI concepts. Covered: 👉 How structured code supports AI workflows 👉 Basics of prompt-based interactions 👉 Thinking in terms of input → processing → intelligent output What I worked on: 👉 Explored simple prompt experiments and observed how responses change 👉 Related my Python fundamentals to how AI systems process data Key takeaway: 👉 Strong programming fundamentals make it easier to understand and build AI systems This marks the beginning of combining core development skills with Generative AI concepts. #Python #AI #GenAI #LearningInPublic #BuildInPublic

 EDA & Feature Engineering 📊 Garbage in = Garbage out. That's why EDA comes first. Before you touch any ML model, you need to understand your data. EDA = Exploratory Data Analysis ✅ Check shape, types, nulls ✅ Plot distributions is it skewed? ✅ Find correlations -heatmaps reveal hidden patterns ✅ Spot outliers before they ruin your model Then comes Feature Engineering — turning raw columns into model fuel: → Encoding categories → Scaling numbers → Creating new features → Dropping irrelevant ones I'm learning this at Humber College, Ontario while building real ML projects 🎓 What's your go-to EDA library -- Pandas Profiling, Seaborn, or Plotly? #EDA #FeatureEngineering #MachineLearning #DataScience #Python #HumberCollege

🚀 Understanding PageRank Through Code-Based Simulation 🌟 I recently worked on a simulation inspired by the PageRank algorithm, where I implemented a directed graph model using Python to understand how importance flows across nodes in a network. In this project: I Built a directed graph using NetworkX Simulated point redistribution across nodes based on outgoing links Observed how rankings evolve over multiple iterations Compared the results with the built-in PageRank algorithm This hands-on approach helped me understand: ✔ How ranking systems work behind search engines ✔ The importance of graph theory in real-world applications ✔ How iterative algorithms converge to stable results 💡 It’s fascinating to see how simple logic can model complex systems like web page ranking! #Python #DataStructures #Algorithms #GraphTheory #PageRank #MachineLearning #DataScience #Coding #Programming #LearnByDoing #ComputerScience #TechProjects #PythonProjects #Developers #LinkedInLearning #EngineeringStudents #CodeNewbie #AI #NetworkAnalysis #StudentProjects

The Art of Focus: Mastering Image Cropping with NumPy! 🎯✂️ Day 86/100 In a world of data noise, the ability to focus on what matters is a superpower. For Day 86 of my #100DaysOfCode journey, I explored Region of Interest (ROI) Extraction. In Computer Vision, we don't always need the full picture. By using NumPy Array Slicing, I can 'zoom in' on specific coordinates to isolate faces, text, or objects for further analysis. Technical Highlights: 🎯 ROI Identification: Mastering the coordinate system to pinpoint and extract sub-matrices from large image arrays. ✂️ Precision Slicing: Leveraging Python's [start:stop] syntax to perform lossless cropping in microseconds. ⚡ Computational Optimization: Learning why reducing image size via cropping is the first step in high-speed object detection. 🤖 AI Preprocessing: Understanding how cropping helps prepare datasets for deep learning models by removing irrelevant background noise. Do check my GitHub repository here : https://lnkd.in/d9Yi9ZsC #100DaysOfCode #ComputerVision #NumPy #Python #BTech #IILM #AIML #ImageProcessing #DataScience #SoftwareEngineering #LearningInPublic #WomenInTech

📊 Project Showcase: Student Performance Predictor Developed a machine learning model to predict student academic performance using features like study time, absences, and parental support. 🔧 Implementation: • KNN Algorithm • Data preprocessing & scaling • Model deployment using Flask • Frontend integration with React This project demonstrates end-to-end ML workflow from data to deployment. 🔗 GitHub Repository: https://lnkd.in/dkwmXV-n #DataScience #MachineLearning #AI #Python #ProjectShowcase

Sometimes the maths makes sense on the page. The intuition comes later - usually when something breaks. Working through Sutton & Barto's Reinforcement Learning: An Introduction has been one of the most rewarding things I've done in my ML journey. But I can't lie; the Bellman equations, policy iteration, Beta posteriors had me stuck. Reading them is one thing. Feeling why they behave the way they do is another. So I built an interactive playground to figure that out. Everything from scratch - just NumPy, no RL libraries, so I could truly understand what is going on under the hood. There's the Github repo for those that want to see how the code is working, then there's the live app for people like me that learn by doing. All concepts have interactive simulations and simplified explanations I'll keep extending it as I work through the rest of the book, which I am so excited for. Hopefully this tool is useful for people - let me know if there are updates or other features you want to see! Try it → [https://lnkd.in/gbdCrC6T] Dive into the code → [https://lnkd.in/gW82E3R5] Read the full write-up on my blog → [https://lnkd.in/gtj2v6PM] #MachineLearning #ReinforcementLearning #Python #Streamlit