The performance of current information processors are predominantly based on complementary metal-oxide-semiconductor (CMOS) transistors. However, CMOS scaling have started to face significant challenges and besides the physical limits, the conventional computing paradigm based on binary logic and Von Neumann architecture is becoming increasingly inefficient with onset of big data revolution and growing complexity of computation. Neuromorphic computing is the state-of-the-art research trend in the field of memory and logic devices where the goal is to build a versatile computer that is efficient in terms of energy and space, homogeneously scalable to large networks of neurons and synapses, and flexible enough to run complex behavioral models of the neocortex as well as networks inspired by neural architectures. The talk will discuss the open questions in the field of neuromorphic computation and future research directions.
The communication presentations (keynote talks, facilitated break-out sessions, posters) will be continuously uploaded in May and June.
Ph. D. Docent (Adj. Prof.) Sayani Majumdar is an Academy Research Fellow at the Department of Applied Physics at Aalto University School of Science, Finland. Previously she worked at University of Turku, Åbo Akademi University in Finland and Massachusetts Institute of Technology (MIT), USA. She is an expert of different nanoscale device fabrication and characterization techniques and currently involved in Neuromorphic computing research. She participated in several COST-Action networking events as a Managing Committee member from Finland and so far co-authored more than 70 peer-reviewed journal articles and book chapters including several invited review articles.
|Helsinki Christ Era Meeting2018_SayaniMajumdar.pdf||1.74 MB|
Shufan Yang is Lecturer (Embedded and Intelligent Systems) at University Glasgow.
Shufan Yang, Paulo Valente Klaine, Richard Demo Souza, João Pedro Battistella Nadas, and Muhammad Ali Imran
Unmanned Aerial Vehicles (UAVs) are being envisioned to be deployed in future cellular networks in a wide range of scenarios, such as to rapidly restore network service after a disaster has happened, provide extra coverage whenever events take place in a city, or to deliver content to very remote locations. In this work, a UAVs applications in future cellular networks is presented with reinforcement learning technique in order to provide intelligence for the UAVs. In addition, a use-case considering a pop-up network scenario, where an event happens in certain locations of a city is also presented and two intelligent RL algorithms are compared.
Reinforcement Learning, Deep neural network, Value Function Approximation
- ‹ previous
- 2 of 2