Interested in AI, machine learning, deep learning and applications to engineering and science? Join us!
This event aims to provide a friendly, inclusive atmosphere and is governed by the NeurIPS Code of Conduct. In the spirit of inclusion, we are open to children to attend, but we will not be providing childcare or supervision.
Veridical Data Science by Prof Bin Yu, Professor at the University of California at Berkeley
Data science is a field of evidence-seeking that combines data with domain information to generate new knowledge. It addresses key considerations in AI regarding when and where data-driven solutions are reliable and appropriate. Such considerations require involvement from humans who collectively understand the domain and tools used to collect, process, and model data. Throughout the data science life cycle, these humans make judgment calls to extract information from data. Veridical data science seeks to ensure that this information is reliable, reproducible, and clearly communicated so that empirical evidence may be evaluated in the context of human decisions. Three core principles: predictability, computability, and stability (PCS) provide the foundation for veridical data science. In this talk we will present a unified PCS framework for data analysis, consisting of both a workflow and documentation, illustrated through iterative random forests and case studies from genomics and precision medicine. More information here.
In the real world, we are often faced with situations where data distributions are shifting over time, and we would like to make predictions about things we have never seen before. These situations fall under the umbrella of "Continual Learning", which has gained popularity in recent years in the AI/ML community. Researchers have focused methods that can adapt to new tasks while preventing “catastrophic forgetting” (e.g. in neural networks) through regularization, generative replay, approximate Bayesian approaches etc. I argue, however, that these are far away from the reality of production environments. In this talk I will present efforts we have been making to bridge this gap, tackling the problem from both research and engineering perspectives.
More information here.
Human (and other animals') motions are strongly dependent on numerous reflexes, but we still do not fully understand how these reflexes are developed. We hypothesize that muscle twitches during our sleep are the key element of this developmental processes, and developed a set of computational neuro-musculo-skeletal models of them for feasibility study. I will be summarizing the results from the following papers:
Blumberg, M.S., Marques, H.G., and Iida, F. (2013). Twitching in Sensorimotor Development from Sleeping Rats to Robots, Current Biology, 23(12): R532-R537.
Marques, H.G., Bharadwaj, A. and Iida, F. (2014). From spontaneous motor activity to coordinated behaviour: A developmental model, PLOS Computational Biology, 10(7): e1003653. doi:10.1371/ journal.pcbi.1003653.
Marques, H.G., Imitiaz, F., Iida, F., and Pfeifer, R. (2013). Self-organisation of reflexive behaviour from spontaneous motor activity, Biological Cybernetics, 107(1): 25-37.
More information here.
