Mr. W. B. Ferguson, K.C

Roger W Ferguson , Jr : Information technology in banking and supervision

I am pleased to speak with you today on technological innovation in the financial services sector. As you may know, technology and its impact have been key areas of focus at the Federal Reserve in recent years. As my colleagues on the Federal Reserve Board have often noted, technological innovation affects not just banking, financial services, and regulatory policy, but also the direction of th...

W 3 , b 3 ) ( W ′ 3 , b ′ 3 ) ( W ′ 2 , b ′ 2 ) ( W ′ 1 , b ′ 1 ) ( W ′ ′

In this paper, we present a deep neural network (DNN)-based acoustic scene classification framework. Two hierarchical learning methods are proposed to improve the DNN baseline performance by incorporating the hierarchical taxonomy information of environmental sounds. Firstly, the parameters of the DNN are initialized by the proposed hierarchical pre-training. Multi-level objective function is t...

W A B W A B Input Hidden Output

A modiication to neural network training algorithms is proposed which decorrelates certain weights within the network while minimising the mean squared error. The technique was developed to facilitate neural network interpretation in image processing problems, partly by allowing to initialise all network weights with one xed, low value. However, it can also be applied to classiica-tion tasks in...

Roger W Ferguson, Jr: Equilibrium real interest rate - theory and application (Central Bank Articles and Speeches)

I want to thank the University of Connecticut for providing me this opportunity to comment on the important and challenging concept of the equilibrium real interest rate and its relevance to monetary policy. I will use this occasion to discuss the role that estimates of the equilibrium real federal funds rate can play in thinking about the desired degree of policy accommodation. Those views, I ...

The Late Mr. John W. Davies