Vyshnavi Sangani’s Post

🚀 I'm both thrilled and amazed by the capabilities of AI in helping me build this project in just one day! Excited to unveil my latest creation: a state-of-the-art system that lets you control your computer's volume using hand gestures! 🤚📈 By leveraging OpenCV and MediaPipe, this innovative solution captures hand landmarks via webcam, adjusting the volume based on the distance between your thumb and index finger. 🎥🔊 Powered by generative AI, this project exemplifies the future of intuitive user interfaces. Dive in and experience seamless volume control! GITHUB LINK: https://lnkd.in/e7pEzNNj #AI #MachineLearning #ComputerVision #Innovation #TechTrends #GenerativeAI #GestureControl #OpenCV #MediaPipe #FutureTech

Friendly reminder workshop 1 of our Generative AI Skills series, "Introduction to AI Literacy," is happening tomorrow. We’re excited to welcome speakers David Marotte and Ven Adamov as they kick off this journey into AI. Missed out on registration for Cohort 1? No worries! Cohort 2 begins in January 2025, and registration is open. Here are the dates: - Introduction to AI Literacy: Wednesday, January 22, 2025, 1:00 - 2:30 pm ET - The Art of Prompt Engineering: Wednesday, January 29, 2025, 1:00 - 2:30 pm ET - AI Tools to Boost Productivity: Wednesday, February 5, 2025, 1:00 - 2:30 pm ET - Use Cases for the Public Sector: Wednesday, February 12, 2025, 1:00 - 2:30 pm ET Each 90-minute workshop will include a live Q&A session. Don’t miss this opportunity to explore AI in the public sector. Register today for Cohort 2. https://bit.ly/48s11sE #AIinPublicSector #IPAC #PublicSectorInnovation #AIWorkshop

I'm thrilled to share my latest project in computer vision! After months of hard work and countless iterations, I'm excited to unveil my own custom model for specific task - e.g., Counting vehicals on highway. 🚀 Performance: With lightning-fast inference times and optimized resource utilization, my model is poised to revolutionize. 🌟 Accuracy: Achieving accuracy on benchmark datasets, my model outperforms existing solutions in [ Counting vehicals on highway]. #ComputerVision #MachineLearning #AI #DeepLearning #Innovation #Technology #Research #DataScience

Face Recognition Initiative Using the Labeled Faces in the Wild (LFW) Dataset! 🎉 This initiative involved developing a high-precision Support Vector Machine (SVM) model to accurately classify facial images. To tackle the challenge of imbalanced data, I implemented techniques to balance the dataset, ensuring better model reliability. ⚖️ I applied dimensionality reduction to manage the large feature space, enhancing efficiency and speeding up processing without losing critical information. ⚡ The model was further optimized using Grid Search for hyperparameter tuning, refining its performance across various settings. Performance evaluation was carried out using classification reports, providing a detailed breakdown of precision, recall, and F1 scores. 📊 I also used heatmaps to visually analyze and identify areas where the model misclassified images, helping to understand its behavior and refine the model for improved accuracy. 🔍 Excited to continue exploring the possibilities in AI and Machine Learning! 🌟 #AI #MachineLearning #FaceRecognition #DataScience #SVM #TechInnovation #GridSearch #ComputerVision #ImbalancedData #Heatmaps #DataDriven

Jump into our newest tutorial and get running with image classification on the BrainChip Akida platform using Edge Impulse. https://lnkd.in/g7bY824V Live now! #edgeai #ai #computervision

want to work on classification of AI Generated faces and Real Faces, I've got you, here is a Multi-character faces dataset. Mainly Generated, but the images for Real Faces are collected from some online datasets. lets see how a model respond to it.

🚀Exciting News! We are thrilled to announce our participation in the 18th European Conference on Computer Vision #ECCV2024, happening from September 29th to October 4th at MiCo Milano! 🌍 As a leader in enabling robust, safe, and trustworthy computer vision models, we’re eager to connect with the brightest minds in the field and share insights on safe and performant machine learning technologies. Stay tuned to learn more about the innovations we'll introduce at this show!💡 #ECCV2024 #ComputerVision #AI #MachineLearning #LatticeFlowAI

Excited to share my latest project on object detection using YOLO! 🚀 Leveraging the power of AIMERS (AI and Machine Learning for Enhanced Recognition Systems), we're pushing the boundaries of real-time detection and recognition #AIMERS  #AIMERSOCIETY  #DATANALYSIS  #AIChallenge #TechInnovation #DataScience #MachineLearning #AIForGood #DataVisualization

📊 NeurIPS Top Research Topics 2022-24: Machine Vision continues to dominate the AI research landscape at the world's leading ML conference. Curious about the evolution of AI research priorities? Check out the complete analysis here: https://lnkd.in/da6-7tMa 24 days - 24 visualizations - the Hugging Face and aiworld_eu open-source calendar! Follow for more 📲 #NeurIPS #AIResearch #MachineLearning #DataScience

🧠💻 Peeking Under the Hood: How We Can Glimpse into the Mind of AI As AI becomes more prevalent in our lives, understanding how these systems "think" is crucial. But how do we peer into the mind of a machine learning model? 🔧 Think of it like being a mechanic diagnosing a car engine: - You listen for unusual sounds - Smell for odd odors - Visually inspect moving parts - Feel for vibrations Similarly, AI researchers have developed tools to understand neural networks. One powerful technique is Grad-CAM (Gradient-weighted Class Activation Mapping). 🔍 Grad-CAM is like shining a light on specific engine parts: - It highlights which parts of an image are most important for the AI's decision - Works with various CNN architectures - Provides high-resolution, class-specific visualizations For example, when classifying a cat image, Grad-CAM might highlight the face, ears, and paws - showing us what the AI considers "cat-like" features. 🚀 This is just the beginning! In my latest blog post, I dive deeper into how we can understand AI systems, including: - Visualizing learned features - Tracing information flow - Identifying impactful inputs - Comparing model behaviors Want to learn more about peering into the AI "black box"? Check out the full post here: https://lnkd.in/gwwPPMHw #ArtificialIntelligence #MachineLearning #DataScience #TechInnovation