Deep Arguing | Adam Gould
💬 Discord: https://discord.gg/h8NVzwnysW 💻 GitHub: https://github.com/centaurinstitute 🤝 LinkedIn: https://www.linkedin.com/company/centaur-ai-institute/ 📢 New Initiative: Neuro-Symbolic Agentic Protocol ⭐ Star us on GitHub https://github.com/centaurinstitute/neuro-symbolic-agentic-protocol — 📝 Abstract: This talk introduces Deep Arguing, a neurosymbolic framework that combines deep neural networks with abstract argumentation for interpretable classification. The approach jointly learns feature representations and an argumentative graph in which training examples act as arguments that support their own labels and attack competing ones, with reasoning performed through differentiable argumentation semantics. This produces a case-based, debate-like explanation structure underlying each prediction while remaining trainable end-to-end across different data modalities. I will discuss the core ideas behind the framework, its connection to earlier work on case-based reasoning with argumentation, and experimental results showing competitive predictive performance alongside improved interpretability. 🔗 Paper Links: https://proceedings.mlr.press/v284/gould25a.html (One more link to come!) 👨🔬 Bio: Adam Gould is a PhD student in the AI4Health Centre for Doctoral Training at Imperial, supervised by Professor Francesca Toni and Dr. Matt Williams. He holds a master's degree in computing, specialising in artificial intelligence and machine learning. His research focuses on developing explainable artificial intelligence models to reason about clinical outcomes in patients with neurological disorders. In particular, Adam explores the use of neurosymbolic AI to construct structured debates based on physical activity data collected from wearable devices. His work aims to support the interpretation and understanding of disease progression in patients diagnosed with primary brain tumours. — 🗨️ 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