Happy to announce the first release of 𝐉-𝐍𝐋𝐑, a 𝐉𝐀𝐗 native Python library for 𝐧𝐨𝐧-𝐥𝐢𝐧𝐞𝐚𝐫 𝐫𝐞𝐜𝐨𝐧𝐜𝐢𝐥𝐢𝐚𝐭𝐢𝐨𝐧, learning, and geometric analysis on constraint manifolds 🎉 The main capabilities of the library: ✅ Projection on arbitrary explicit (charts) or implicit manifolds 📐 ✅ Mesh generation on 3D manifolds 🌐 ✅ Efficient computation of geodesic paths and distances. 🐜 ✅ (Curvature-based) sampling of explicit/implicit manifolds 🥏 ✅ Dynamic visualisation tools to visualise 3D data 🧿 J-NLR leverages JAX’s hardware acceleration and auto-diff to make geometric analysis faster. Any feedback is welcome! #JAX #MachineLearning #DifferentialGeometry #Python #OpenSource #GeometricDeepLearning

Here is the research paper associated with the JNLR library. https://lnkd.in/gqZamwiq The library can be extended to compute Mean and Gaussian curvature by extracting max eigenvalues in the tangent space (max_tangent_eigenvalue ) #JAX #JNLR #ManifoldCurvature

How can you evaluate an AI model's robustness before real-world failures occur? In this webinar, we’ll demonstrate how to use the open source Natural Robustness Toolkit (NRTK) to create reproducible workflows for testing model performance. You’ll learn how to: ✅ Install and configure NRTK in Python ✅ Apply perturbations to expand existing datasets ✅ Design parameter sweeps to measure performance degradation ✅ Evaluate models under simulated operational conditions 📅 April 15, 2026 | 12–1 PM 👉 Register here: https://ow.ly/Ncnr50YBmK7 #AIResearch #MachineLearning #ModelValidation #NRTK #Python

I recently worked on a small spectroscopy project where I explored how to identify peaks in a noisy UV-Vis spectrum using Python. The workflow involved: • Simulating spectral data • Applying Savitzky–Golay smoothing • Detecting peaks with SciPy • Visualizing the results One thing that stood out to me was how sensitive peak detection is to parameter choices a small tweak can completely change the outcome. This project helped me better understand signal processing in a practical way, especially within a chemistry context. I’m continuing to explore more ways to combine data analysis with chemistry. https://lnkd.in/eVCs9wYT https://lnkd.in/eK8iJDnv #DataAnalytics #Python #Spectroscopy #LearningInPublic

🚗 Built an Automatic Number Plate Recognition (ANPR) System! Excited to share my recent project where I developed a real-time ANPR system using YOLOv8 and EasyOCR. 🔍 Key Features: • Real-time number plate detection • OCR-based text extraction • Custom dataset creation This project helped me strengthen my skills in Computer Vision and Machine Learning. 🔗 GitHub Repository: https://lnkd.in/g_5r5wcW #MachineLearning #ComputerVision #YOLO #Python #DataScience

📊 Day 6 | K-Nearest Neighbors (KNN) 🤝📍 Today, I learned about K-Nearest Neighbors (KNN), a simple and intuitive Machine Learning algorithm. KNN works on the idea of distance — it classifies a data point based on the majority class of its nearest neighbors. 📌 In simple terms: “Similar data points are close to each other.” Example: ✔ Recommending products ✔ Classifying customers To understand this, I implemented KNN using Python and observed how it predicts based on nearby data points 💻 KNN is simple but powerful for many classification problems. #MachineLearning #KNN #DataScience #LearningInPublic #Python

🌸 Iris Model Explained | OASIS Task 🌸 In this video, I break down the complete workflow of iris_model.py — from understanding the dataset to building and evaluating the model. 📊✨ 🔍 Key highlights: • Data loading and exploration • Preprocessing steps • Model building and training • Performance evaluation This explanation simplifies how machine learning models work using the classic Iris dataset 🌿 #MachineLearning #Python #DataScience #OASISInfobyte #IrisDataset #EDA #ModelBuilding

Built an Interactive Computer Vision Image Processing Toolkit using OpenCV and Streamlit. This project focuses on implementing core image processing operations and making them accessible through a simple web interface. Key functionalities: • Grayscale conversion • Canny edge detection for boundary extraction • Gaussian blur for noise reduction • Sepia filter using matrix transformation • Image rotation using affine transformations Tech Stack: Python, OpenCV, NumPy, Streamlit Key takeaways: • Improved understanding of image transformations and filtering • Learned practical challenges like BGR vs RGB inconsistencies • Built an interactive pipeline for real-time image processing GitHub: https://lnkd.in/gWXEGTNk Open to feedback and opportunities in Computer Vision / ML roles. #ComputerVision #OpenCV #Python #MachineLearning #SkillArbitrage #NSDC

𝗗𝗮𝘆 𝟯 | 𝗢𝗽𝗲𝗿𝗮𝘁𝗼𝗿𝘀 𝗮𝗻𝗱 𝗯𝗮𝘀𝗶𝗰 𝗶𝗻𝘁𝗲𝗿𝗮𝗰𝘁𝗶𝗼𝗻 Today’s session felt more practical compared to the previous ones, as I started working with operations and user interaction. 𝗧𝗼𝗽𝗶𝗰𝘀 𝗰𝗼𝘃𝗲𝗿𝗲𝗱: 💠 Arithmetic operators such as addition, subtraction, multiplication, and division 💠 Comparison operators like greater than, less than, and equal to 💠 Logical operators including and, or, and not 💠 Taking input from the user using input() 💠 Displaying output using print() Combining these concepts in small programs made things clearer. It now feels like I am actually using Python rather than just understanding theory, and that shift is making the learning more interesting. #Python #Operators #CodingBasics #DataAnalysis #LearningJourney

Not every day is about solving problems, some days are about understanding concepts. Day 38/100 — Data Structures & Algorithms Journey Today I focused on learning the Sliding Window technique instead of solving problems. Taking time to understand the pattern deeply before jumping into implementation. Today’s Focus: Understanding how sliding window works Learning when to expand and shrink the window Studying problem patterns where it applies Building intuition step by step Why this matters? Because strong concepts make problem-solving faster and more efficient. Key Takeaways: Learning is also progress Clarity builds confidence Patterns simplify complex problems Consistency matters more than intensity Taking it slow, but moving forward #Day38 #DSA #LeetCode #ProblemSolving #CodingJourney #100DaysOfCode #SoftwareEngineering #Python #InterviewPreparation #LearnInPublic #Consistency