报告内容简介：

The amazing progress of neural networks has given us clues about how the brain might perform some of the tasks that we consider to be intelligent: visual recognition, natural language understanding, strategic game playing, etc. However, these architectures are quite different from the networks of neurons in your brain, so it’s still not clear how people manage to learn and perform these tasks. One promising theory is predictive coding. I will describe a recent predictive coding approach, and show some preliminary results for how this theory matches our own brains better than most neural networks.

报告人简介：

Jeff Orchard博士，加拿大滑铁卢大学计算机学院教授，计算数学系系主任。1994年毕业于滑铁卢大学数学专业获学士学位，1996年毕业于加拿大英属哥伦比亚大学数学专业获硕士学位，2003年毕业于加拿大西蒙弗雷泽大学获计算机科学博士学位。研究方向为计算神经科学，通过数学模型和计算机仿真来理解大脑的复杂运行机理。在基底核网络的决策模型、视觉网络的无监督学习、空间浏览、种群编码、医疗图象处理等领域做出了突出贡献，在IEEE Transactions on Neural Networks and Learning Systems、IEEE Transactions on Image Processing、IEEE Transactions on Medical Imaging、Neural Computation等顶级刊物和会议上发表高水平论文。