Deploying Machine Learning Models with FastAPI and Docker
Deploying a machine learning model can be a complex process. FastAPI and Docker offer a streamlined way to package and deploy a machine learning model, making it easier to share the work with others or integrate it into a larger application.
By using FastAPI and Docker to deploy the machine learning model, you can benefit from faster development time, greater flexibility, and easier collaboration. This presentation will cover the basics of creating a Machine Learning model, using FastAPI to expose the model via a REST API, and deploying the Web Service with a Docker container.
AI Security: Protecting Models, APIs, and Pipelines
AI applications are becoming more powerful and widespread, but with that growth comes increasing security threats. From adversarial inputs and model inference attacks to output injection, API abuse, and knowledge distillation, AI systems face a range of risks that can compromise their integrity, reliability, and safety.
In this presentation, we’ll explore best practices for securing AI applications, including input validation, output moderation, access controls, monitoring, continuous updates, etc. Additionally, we’ll discuss how AI-driven mitigation models can enhance security by detecting and responding to emerging threats in real time.
Finally, we’ll dive into techniques for making AI models distillation-proof, ensuring that proprietary knowledge remains protected against extraction attempts. By the end of this session, you’ll have actionable strategies to strengthen your AI systems against evolving security challenges.
Agents 2.0: Building Deep, Self-Reflective, and Autonomous AI Systems
AI is evolving from prompt responders to autonomous thinkers. In this session, we’ll explore how “Deep Agents” reason, plan, and reflect on their actions to achieve complex goals. Through live demonstrations, you’ll see the leap from simple model interactions to self-correcting, multi-step reasoning systems. Learn the architecture, design patterns, and implementation techniques behind this new generation of intelligent, goal-driven AI.
Advancing AI Reasoning: Exploring Self-Reflection and Self-Attention in Large Language Models
In this presentation, we explore the evolving landscape of AI reasoning through the lens of Large Language Models (LLMs). We will dive into how self-attention mechanisms enable LLMs to process and generate coherent responses, while introducing the concept of self-reflection in AI agents, allowing them to evaluate and refine their own outputs. By understanding these processes, we can better grasp the potential and challenges in developing more advanced, autonomous AI systems capable of complex reasoning.
Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.
Jump to top