Neurosymbolic AI for Interpretable Image Classification | Parth Padalkar | Neuro-Symbolic Wednesdays скачать в хорошем качестве

Neurosymbolic AI for Interpretable Image Classification | Parth Padalkar | Neuro-Symbolic Wednesdays

💬 Discord:   / discord   💻 GitHub: https://github.com/centaurinstitute 🤝 LinkedIn:   / centaur-ai-institute   📢 New Initiative: Neuro-Symbolic Agentic Protocol ⭐ Star us on GitHub https://github.com/centaurinstitute/n... — ​​📘 This week, Parth Padalkar will give a talk on "Neuro-Symbolic AI for Interpretable Image Classification" 🎤 Modern AI systems can recognize images, understand language, and solve complex tasks, but they often operate as “black boxes,” making it difficult to understand why they make certain decisions. This lack of transparency is a major challenge in high-stakes domains like healthcare, transportation, and public safety. My research focuses on building AI models that are both powerful and interpretable. ​In this talk, I will show how symbolic reasoning and logic can be combined with neural networks to produce clear, rule-based explanations of model decisions. I will demonstrate how image classifiers and Vision Transformers can be translated into compact logical rules that reveal what the model has learned, without sacrificing accuracy. These explanations can also help detect and correct biased or misleading behavior. 🎓 Parth Padalkar is a Ph.D. candidate and Templeton Graduate Fellow in Computer Science at The University of Texas at Dallas. His research focuses on neuro-symbolic AI, explainable AI, and building reliable and interpretable neural models by combining deep learning with logic programming. He has published research at venues such as the AAAI Conference on Artificial Intelligence and the International Conference on Logic Programming. He is passionate about making modern AI systems understandable, trustworthy, and aligned with human reasoning. — 🗨️ ​Join us for an interactive session exploring Neuro-Symbolic AI, the emerging paradigm that blends the strengths of neural networks with symbolic reasoning. We will discuss how hybrid approaches can enhance generalization, interpretability, and reasoning, and how these methods are shaping the future of intelligent systems. Whether you’re a researcher, engineer, or simply curious about the cutting edge of AI, you’ll find an engaging space to learn, connect, and exchange ideas. Event Format: 🔍 Reading Group 🎙️ Panel Discussion 🧩 Tutorials/Workshop Series 💬 Research Roundtable 🛠️ Open-Source Project Review 📄 Paper Pitch 🤝 Collaboration Hour 🍵 Networking Mixer #AI #NeuroSymbolic #FutureOfAI