Large language models (LLMs) have advanced the field of artificial intelligence (AI) and are a powerful enabler for interactive systems. However, they still face challenges in long-term interactions that require adaptation towards the user as well as contextual knowledge and understanding of the ever-changing environment. To overcome these challenges, holistic memory modeling is required to efficiently retrieve and store relevant information across interaction sessions for suitable responses. Cognitive AI, which aims to simulate the human thought process in a computerized model, highlights interesting aspects, such as thoughts, memory mechanisms, and decision-making, that can contribute towards improved memory modeling for LLMs. Inspired by these cognitive AI principles, we propose our memory framework CAIM. CAIM consists of three modules: 1.) The Memory Controller as the central decision unit; 2.) the Memory Retrieval, which filters relevant data for interaction upon request; and 3.) the Post-Thinking, which maintains the memory storage. We compare CAIM against existing approaches, focusing on metrics such as retrieval accuracy, response correctness, contextual coherence, and memory storage. The results demonstrate that CAIM outperforms baseline frameworks across different metrics, highlighting its context-awareness and potential to improve long-term human-AI interactions.

The Center for Artificial Intelligence in Medicine (CAIM) will be officially opened in January 2021 in Bern, Switzerland. The center, founded by the University of Bern and the Inselspital, University Hospital of Bern, is intended to be a platform for research, teaching and transfer of medical technologies using AI, aimed at improving the provision of patient care and facilitating the work of physicians and caregivers. The healthcare sector today generates more data than healthcare professionals are able to analyze. AI allows us to use this data to determine the characteristics that doctors, caregivers and other health professionals need to make more accurate diagnoses and better treatment decisions. With AI, treatments become more accurate – unnecessary interventions can be avoided and treatment successes improved. In cancer therapy, for example, treatment plans can be designed more specifically for the patient to minimize radiation exposure.

The potential of Artificial Intelligence (AI) to tackle challenging problems that afflict society is enormous, particularly in the areas of healthcare, conservation and public safety and security. Many problems in these domains involve harnessing social networks of under-served communities to enable positive change, e.g., using social networks of homeless youth to raise awareness about Human Immunodeficiency Virus (HIV) and other STDs. Unfortunately, most of these real-world problems are characterized by uncertainties about social network structure and influence models, and previous research in AI fails to sufficiently address these uncertainties. This thesis addresses these shortcomings by advancing the state-of-the-art to a new generation of algorithms for interventions in social networks. In particular, this thesis describes the design and development of new influence maximization algorithms which can handle various uncertainties that commonly exist in real-world social networks. These algorithms utilize techniques from sequential planning problems and social network theory to develop new kinds of AI algorithms. Further, this thesis also demonstrates the real-world impact of these algorithms by describing their deployment in three pilot studies to spread awareness about HIV among actual homeless youth in Los Angeles. This represents one of the first-ever deployments of computer science based influence maximization algorithms in this domain. Our results show that our AI algorithms improved upon the state-of-the-art by 160% in the real-world. We discuss research and implementation challenges faced in deploying these algorithms, and lessons that can be gleaned for future deployment of such algorithms. The positive results from these deployments illustrate the enormous potential of AI in addressing societally relevant problems.

The world of Artificial Intelligence today is still centered around the aspiration for machines to understand: from virtual assistants capable of anticipating our needs and helping us drafting emails or handling our complex schedule, to self-driving cars, and personalized medicine. These are just some examples of how machines need to acquire, demonstrate, and apply understanding. Today's investments in public research and in the private sector are directed at cracking the nut of machines that understand. But the breadth of techniques goes well beyond what it did even ten years ago. In light of today's relevance of Cognitive Artificial Intelligence, we are happy to announce the Cognitive Artificial Intelligence Meetup #CAIM ("Kay-im").