Math Machine Learning Group Seminar


22.05.20	Hui Jin (University of California, Los Angeles) : Implicit bias of gradient descent on wide neural networks
15.05.20	Thomas Merkh (University of California, Los Angeles) : Recurrences and transfer methods for counting activation patterns in CNNs
08.05.20	Yoni Dukler (University of California, Los Angeles) : Deep Learning for Self Driving In this talk, I will give an overview of the current state and common methodologies of self driving technologies. Due to the advancements in hardware, and the wealth of data being collected by such systems, deep learning algorithms are emerging to be crucial and I will survey the common uses of deep learning for self driving. Lastly as a theoretician, I will go over avenues and challenges in self driving systems that can benefit from improved theoretical understanding and deep learning theory. The purpose of this talk is to introduce deep learning researchers to the field and present some of the most pressing issues faced by self driving practitioners in the hopes of advancing the field as a whole.