New video out today — this time on the PyCharm channel! We built a TensorFlow model from scratch, step by step, using a Jupyter notebook inside PyCharm. The goal was to make it genuinely beginner-friendly: no assumptions, no hand-waving, just actual code that runs. What we covered: — Loading and visualising a real dataset (fashion images — much more fun than MNIST) — Building and comparing two different model architectures — Evaluating accuracy and actually understanding what the number means — Digging into where the model gets confused and why (spoiler: shirts and pullovers are hard) — Using PyCharm's AI assistant to speed up the parts that don't need to be slow One thing I always try to do in these videos: show the thinking, not just the result. Why do we normalise the pixel values? Why ReLU? Why does the second model not actually justify its extra training time? If you're getting started with TensorFlow or just want to see how a clean ML workflow looks inside a proper IDE — this one's for you. 👉 https://lnkd.in/eAXj8K-F #TensorFlow #MachineLearning #Python #PyCharm #JetBrains JetBrains

This video is a collaboration with JetBrains — produced for the PyCharm channel as part of an ongoing DevRel partnership. It's a good example of what that kind of work looks like in practice: a technically honest, hands-on tutorial that serves the audience first and happens to showcase the tool naturally along the way. This is exactly the kind of content production I'm open to doing with more teams in 2026. If you work at a developer tools, AI, or robotics company and want to reach a technical audience through video content that actually gets watched - I'd love to talk. The Back to Engineering channel covers Physical AI, robotics, and embedded systems. But the production model of deep technical content, learn-in-public format, real code on screen translates across the developer tooling space. #DevRel #DeveloperEducation #TechnicalContent #BackToEngineering #JetBrains

Developed a mini game using Python to help students explore the fundamentals of collision handling. Instead of just learning theory, this approach lets them see and interact how the collisions handles really by machines. This game is just explaining about the Types of Collision Handling: 1. Separate Chaining (Open Hashing) 2. Open Addressing (Closed Hashing): Linear Probing: Checks the very next slot(index to store the data) This is what you used in your game! Quadratic Probing Double Hashing Turning concepts into visual experiences really helps deepen understanding. Looking forward to building more such learning tools! #python #DSA #LearningByDoing #ComputerScience #DataScience

Here’s a new beginner-friendly tutorial I wrote on Geo AI for Industrial Engineering using Python. It walks through a simple hands-on mini-project: preparing location data, running light clustering, and visualizing the results on an interactive map. The goal is to make Geo AI feel practical and approachable, especially for students and early learners who want to see how spatial intelligence can support real decision-making. A good reminder that sometimes the best way to understand a new concept is not to start with heavy theory, but to build something small that makes the idea visible. https://lnkd.in/gTAs_5Bb #GeoAI #IndustrialEngineering #Python #DataVisualization

Reinforcement Learning is a subfield of machine learning that involves an agent learning to take actions in an environment to maximize a reward, learn more with Python and Gym https://lnkd.in/g233cAvV #ReinforcementLearning Read the full article https://lnkd.in/g233cAvV

Built a GenAI application that converts YouTube videos into structured articles, downloadable PDFs, and responsive webpages. The system uses a multi-step pipeline: transcript extraction, content cleaning, article generation, and multi-format output creation. Tech stack: Python, Streamlit, LangChain, Groq (LLaMA 3.3), FPDF This project helped me understand how to design end-to-end GenAI workflows beyond simple summarization. 🔗 GitHub: https://lnkd.in/gygZUgGG #Innomaticsresearchlabs #GenerativeAI #Langchain #Python #Datascience

Day 4 of my Machine Learning journey 🚀 Explored Min-Max Scaling technique to normalize feature values between 0 and 1. Learned why scaling is important when features have different ranges and how it impacts model performance. Building strong fundamentals in machine learning step by step 💪 #MachineLearning #Python #DataScience #ML #Learning

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've been using AI agents every day for months without actually understanding how they work. A cracked friend built a tool that breaks the whole thing down. No frameworks. ~60 lines of Python. Turns out an agent is just a function. Tools are a dict. Memory is a tool that writes to a file. That's it. Went through all 9 lessons in one sitting. If you've been using LangChain or CrewAI without knowing what's underneath, honestly just start here first. #AIAgents #SoftwareEngineering #BuildingInPublic

🚀 Built my first RAG (Retrieval-Augmented Generation) Chatbot using Python! Instead of guessing, this chatbot reads, understands, and answers directly from custom data 📄➡️🤖 Powered by FAISS, HuggingFace embeddings, and Groq LLM, it delivers fast and context-aware responses. 💡 From static text → to intelligent conversations This is a small step into the world of AI-powered applications, but a big leap in how machines interact with knowledge. #AI #MachineLearning #LangChain #Python #RAG #GenAI #DataScience