|
在层次结构中学习：从神经科学到衍生核心
Learning in Hierarchical Architectures: from Neuroscience to Derived Kernels |
|
| |
| 课程网址: |
http://videolectures.net/mlss09us_poggio_lhandk/
|
| 主讲教师: |
Tomaso A. Poggio
|
| 开课单位: |
麻省理工学院
|
| 开课时间: |
2009-07-30
|
| 课程语种: |
英语
|
| 中文简介: |
理解我们皮层中信息的处理是理解大脑如何工作的重要部分，可以说是当今科学中最大的问题之一。特别是，我们的视觉能力在计算上是惊人的：计算机科学仍远未能够创造出模仿它们的视觉引擎。因此，视觉皮层及其执行的计算问题很可能是其他皮层和智能本身的良好代理。
我将简要回顾一下我们基于灵长类视觉皮层的解剖学和生理学开发用于物体识别的分层前馈架构的工作。这些架构与最先进的计算机视觉系统竞争;它们模仿人类在特定但困难的自然图像识别任务中的表现。我将描绘当前的工作，旨在将模型扩展到识别图像时间序列中的行为，并考虑到人类视觉中的注意力效应。
然后，我将描述一种新的尝试（与S. Smale，L。Rosasco和J. Bouvrie合作）为分层内核机器开发数学，该机器以递归定义的“派生内核”的概念为中心，并由模型和底层直接建议视觉皮层的神经科学。
|
| 课程简介: |
Understanding the processing of information in our cortex is a significant part of understanding how the brain works, arguably one of the greatest problems in science today. In particular, our visual abilities are computationally amazing: computer science is still far from being able to create a vision engine that imitates them. Thus, visual cortex and the problem of the computations it performs may well be a good proxy for the rest of the cortex and for intelligence itself.
I will briefly review our work on developing a hierarchical feedforward architecture for object recognition based on the anatomy and the physiology of the primate visual cortex. These architectures compete with state-of-the-art computer vision systems; they mimic human performance on a specific but difficult natural image recognition task. I will sketch current work aimed at extending the model to the recognition of behaviors in time sequences of images and to accounting for attentional effects inhuman vision.
I will then describe a new attempt (with S. Smale, L. Rosasco and J. Bouvrie) to develop a mathematics for hierarchical kernel machines centered around the notion of a recursively defined "derived kernel" and directly suggested by the model and the underlying neuroscience of the visual cortex.
|
| 关 键 词: |
视觉引擎; 分层前馈架构; 计算机视觉系统竞争
|
| 课程来源: |
视频讲座网
|
| 最后编审: |
2019-07-18：cjy
|
| 阅读次数: |
37
|
|
图 书 馆