AI and Machine Learning

Colorizing old black-and-white videos and "bringing faces to life" for FREE SVFR — a full-fledged framework for restoring faces in videos. It can: 💬 BFR — improve blurry faces. 💬 Colorization — colorize black-and-white videos. 💬 Inpainting — redraw damaged areas. 💬 and combine all of this in one pass. Essentially, the model takes old or damaged videos and makes them "as if they were shot yesterday". And it's free and open-source. ⚙️ Installation locally: 1. Create an environment

conda create -n svfr python=3.9 -y
conda activate svfr

2. Install PyTorch (for your CUDA)

pip install torch==2.2.2 torchvision==0.17.2 torchaudio==2.2.2

3. Install dependencies

pip install -r requirements.txt

4. Download models

conda install git-lfs
git lfs install
git clone https://huggingface.co/stabilityai/stable-video-diffusion-img2vid-xt models/stable-video-diffusion-img2vid-xt

5. Start processing videos

python infer.py \
--config config/infer.yaml \
--task_ids 0 \
--input_path input.mp4 \
--output_dir results/ \
--crop_face_region

Where task_ids: * 0 — face enhancement * 1 — colorization * 2 — redrawing damage An ideal tool if: 🟢you're restoring archival videos; 🟢you're creating historical content; 🟢you're working with neural networks and video effects; 🟢you want a wow result without paid services. ▶️ Demo on Hugging Face 🌐 GitHub/Instructions

🔅 Responsible AI Framework for Your Enterprise AI Product 📝 Master responsible AI with the Five Rings framework. Learn how to build ethical, secure, and transparent AI products that align with human values and business success. 🌐 Author: Alina Zhang 🔰 Level: Intermediate ⏰ Duration: 45m 📋 Topics: Responsible AI, Artificial Intelligence 🔗 Join Artificial intelligence for more courses

🔁 K-Fold Cross Validation K-Fold exists to answer one honest question: Will this model work on unseen data? A single train/test split is unreliable, especially with small datasets. So K-Fold simulates multiple “future tests” using the same data. 🧠 What It Really Does Instead of one split, we: 🔀 Divide data into K folds 🔁 Train the model K times 📦 Each time: one fold validates, the rest train 📊 Average the scores Every sample gets validated once, which reduces evaluation noise and gives a more trustworthy estimate. Important: It improves evaluation, not the model itself. ⚠️ What People Often Miss 🚫 Do NOT use K-Fold as your final test. Keep a separate test set ⚖️ Use Stratified K-Fold for imbalanced classification. ⏳ Do NOT use standard K-Fold for time series. 📊 K = 5 or 10 is usually enough. ✅ In short K-Fold is just: A smart way to reuse limited data to simulate multiple real-world tests. No magic. Just careful evaluation.

📌 A comprehensive masterclass on Claude Code is available via this repository: https://github.com/luongnv89/claude-howto. This resource provides a detailed visual and practical guide for one of the most powerful tools for developers. The repository includes: • Step-by-step learning paths covering basic commands (/init, /plan) to advanced features such as MCP, hooks, and agents, achievable in approximately 11–13 hours. 📚 • An extensive library of custom commands designed for real-world tasks. • Ready-made memory templates for both individual and team workflows. • Instructions and scripts for: - Automated code review. - Style and standards compliance checks. - API documentation generation. • Automation cycles enabling autonomous operation of Claude without direct user intervention. ⚙️ • Integration with external tools, including GitHub and various APIs, presented with step-by-step guidance. • Diagrams and charts to facilitate understanding, suitable for beginners. 📊 • Examples for configuring highly specialized sub-agents. • Dedicated learning scripts, such as tools for generating educational books and materials to master specific topics efficiently. Access the full guide here: https://github.com/luongnv89/claude-howto

🔅 Deep Learning with TensorFlow: Insights and Innovations 📝 Explore the evolving world of deep learning with TensorFlow, including the basics of generative AI, with practical, hands-on examples. 🌐 Author: Isil Berkun 🔰 Level: Intermediate ⏰ Duration: 3h 6m 📋 Topics: TensorFlow, Deep Learning, Artificial Intelligence 🔗 Join Artificial intelligence for more courses

100 AI ML projects for all levels

100 AI ML projects for all levels

🔅 A Content Marketer's Guide to Responsible AI 📝 Learn to use AI responsibly in content marketing, balancing personalization, privacy, and ethical AI practices. 🌐 Author: Lauren Diethelm 🔰 Level: General ⏰ Duration: 23m 📋 Topics: Content Marketing, Artificial Intelligence for Business 🔗 Join Artificial intelligence for more courses

AI Agents vs Agentic AI... what’s the actual difference?

There are 3 types of AI workflows worth knowing and each performs a different task. If you don’t understand these you’re probably falling behind.

Non-Agentic AI: Basic prompt-response AI with no memory/reasoning. They’re fast, cheap, and universally accessible, requires no technical build or integration and great for clear, one-off tasks. Agentic AI: Self-managing AI system that can plan and execute. Great for handling complex, changing projects. They can integrate with tools and databases and produce more reliable outcomes. AI Agent: A single-task AI worker designed to automate one task. Automates repetitive, time-consuming tasks, quick setup and cost-efficient and easy to test and refine within roles In short: AI Agents = Single-task automation Agentic AI = Multi-step problem solving