智能科学课程考核的相关

下周末智能科学考核，主要还是做PPT。这次考核难度比较大，70到80分钟。

于是先查比较重要的会议论文，刚查到A类会议之上还有A+这个级别的。CCF把A类会议挪到一区SCI级别了，曾经投过的ICDE在这个版本里也成了A+。http://blog.csdn.net/cserchen/article/details/40508181

AAAI	National Conference of the American Association for Artificial Intelligence	A+
AAMAS	International Conference on Autonomous Agents and Multiagent Systems	A+
ACL	Association of Computational Linguistics	A+
ACMMM	ACM Multimedia Conference	A+
ASPLOS	Architectural Support for Programming Languages and Operating Systems	A+
CAV	Computer Aided Verification	A+
CCS	ACM Conference on Computer and Communications Security	A+
CHI	International Conference on Human Factors in Computing Systems	A+
COLT	Annual Conference on Computational Learning Theory	A+
CRYPTO	Advances in Cryptology	A+
CSCL	Computer Supported Collaborative Learning	A+
DCC	IEEE Data Compression Conference	A+
DSN	International Conference on Dependable Systems	A+
EuroCrypt	International Conference on the Theory and Application of Cryptographic Techniques	A+
FOCS	IEEE Symposium on Foundations of Computer Science	A+
FOGA	Foundations of Genetic Algorithms	A+
HPCA	IEEE Symposium on High Performance Computer Architecture	A+
I3DG	ACM-SIGRAPH Interactive 3D Graphics	A+
ICAPS	International Conference on Automated Planning and Scheduling	A+
ICCV	IEEE International Conference on Computer Vision	A+
ICDE	IEEE International Conference on Data Engineering	A+
ICDM	IEEE International Conference on Data Mining	A+
ICFP	International Conference on Functional Programming	A+
ICIS	International Conference on Information Systems	A+
ICML	International Conference on Machine Learning	A+
ICSE	International Conference on Software Engineering	A+
IJCAI	International Joint Conference on Artificial Intelligence	A+
IJCAR	International Joint Conference on Automated Reasoning	A+
INFOCOM	Joint Conference of the IEEE Computer and Communications Societies	A+
InfoVis	IEEE Information Visualization Conference	A+
IPSN	Information Processing in Sensor Networks	A+
ISCA	ACM International Symposium on Computer Architecture	A+
ISMAR	IEEE and ACM International Symposium on Mixed and Augmented Reality	A+
ISSAC	International. Symposium on Symbolic and Algebraic Computation	A+
ISWC	IEEE International Symposium on Wearable Computing	A+
IWQoS	IFIP International Workshop on QoS	A+
JCDL	ACM Conference on Digital Libraries	A+
KR	International Conference on Principles of KR & Reasoning	A+
LICS	IEEE Symposium on Logic in Computer Science	A+
MOBICOM	ACM International Conferencem on Mobile Computing and Networking	A+
NIPS	Advances in Neural Information Processing Systems	A+
OOPSLA	ACM Conference on Object Oriented Programming Systems Languages and Applications	A+
OSDI	Usenix Symposium on Operating Systems Design and Implementation	A+
PERCOM	IEEE International Conference on Pervasive Computing and Communications	A+
PERVASIVE	International Conference on Pervasive Computing	A+
PLDI	ACM-SIGPLAN Conference on Programming Language Design & Implementation	A+
PODC	ACM Symposium on Principles of Distributed Computing	A+
PODS	ACM SIGMOD-SIGACT-SIGART Conferenceon Principles of Database Systems	A+
POPL	ACM-SIGACT Symposium on Principles of Prog Langs	A+
RSS	Robotics: Systems and Science	A+
RTSS	Real Time Systems Symp	A+
SENSYS	ACM Conference on Embedded Networked Sensor Systems	A+
SIGCOMM	ACM Conference on Applications, Technologies,Architectures, and Protocols for Computer Communication	A+
SIGGRAPH	ACM SIG International Conference on Computer Graphics and Interactive Techniques	A+
SIGIR	ACM International Conference on Research and Development in Information Retrieval	A+
SIGKDD	ACM International Conference on Knowledge Discovery and Data Mining	A+
SIGMETRICS	ACM SIG on computer and communications metrics and performance	A+
SIGMOD	ACM Special Interest Group on Management of Data Conference	A+
SODA	ACM/SIAM Symposium on Discrete Algorithms	A+
SOSP	ACM SIGOPS Symposium on Operating Systems Principles	A+
STOC	ACM Symposium on Theory of Computing	A+
UAI	Conference in Uncertainty in Artifical Intelligence	A+
UbiComp	Uniquitous Computing	A+
VLDB	International Conference on Very Large Databases	A+
WWW	International World Wide Web Conference	A+

*****

刚在知网上找对应论文，居然弹出并发数达到最大。

生物信息与智能科学，很多书还有文献狭义上的意思就是把统计学习方法用到生物信息上。

VC维：对于一个指示函数集，如果其生长函数是线性的，则它的VC维为无穷大；而如果生长函数以参数为h的对数函数为上界，则函数集的VC维是有限的且等于h。

又函数集学习过程一致收敛的充分必要条件，对任意的样本分布，都有lim[G(n)/n]=0，且这时学习过程收敛速度一定是快的。G(n)为指示函数集的生长函数。

这涉及信息论和熵的问题。于是昨天杜老师提到了卡诺循环热力学定律等等。于是也查了一下。

热力学第一定律是能量守恒定律。 热力学第二定律有几种表述方式： 克劳修斯表述为热量可以自发地从温度高的物体传递到温度低的物体，但不可能自发地从温度低的物体传递到温度高的物体；开尔文-普朗克表述为不可能从单一热源吸取热量，并将这热量完全变为功，而不产生其他影响。以及熵增表述：孤立系统的熵永不减小。 热力学第三定律通常表述为绝对零度时，所有纯物质的完美晶体的熵值为零， 或者绝对零度（T=0）不可达到。

之后搜索引擎右面一堆奇谈怪论。看了之后不如不看。。

回到正题。

昨天杜老师的课主题就是提特征比后期统计学习方法更对提高预测精度有更多影响。貌似现在信号处理之类的都大量地用了。

于是PPT的框架基本清楚了，就是把目前的研究工作作为主要内容，外加一堆生物信息基本知识。