背景：NYCU CS 大二必修演算法教授：游逸平/學分：3總結來說很不錯的課，整堂課總共五個程式作業，都是上機寫Code的那種，期中末都有分成手寫與上機考，手寫還算簡單，有認真讀一下應該還好，上機說實話也沒有很難，大部分都是模板題或稍有一點變化，老師上課也不錯，講解的內容都算讓人聽得懂。這堂應該是三個演算法裡面最硬的，不過因為都修過競程（一）了，我本來想說演算法應該是水課吧，但我有...
TreesDefinition 3.1
acyclic: if there are no cycles or circuits in the graph.
tree: acyclic and connected.
forest: acyclic graph.
leaf: vertex with degree 1.
Spanning TreesDefinition 3.2A spanning...
Graph RoutesDefinition 2.1
A walk is a sequence of vertices so that there is an edge between consecutive vertices. A walk can repeat vertices and edges.
A trail is a walk with no repeated edges. A ...
Graph Models and TerminologyTerminologyDefinition 1.1
A graph GGG consists of two sets: V(G)V(G)V(G), called the vertex set, and E(G)E(G)E(G), called the edge set. An edge, denoted xy, is an unorde...
Training data-efficient image transformers & distillation through attention(DeiT)Published Year : 2020Paper URL
WhatThis paper introduce a new model called DeiT. The main different between DeiT...
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale (Vision Transformer)Published Year : 2021Paper URL
What
CNNs dominated classification tasks until recently. This paper sho...
交大應數轉資工 心得基本上轉資工第一個看 GPE，第二個看 GPANote : 這篇文只專注在如何在交大轉入資工，其他系我就不是很清楚
什麼是 GPEGPE(General Programming Exam)是類似 CPE 的考試，是一種檢定程式能力的考試，給定要求的輸入，並照著題要求生出正確的輸出，基本上就是程式競賽，總共會有六題，考試時間長達四個小時，每一題都會有分配部份分，根據你所使用...
Deep residual Learning for Image Recognition
Published Year : 2015
Paper URL
WhatDeeper neural networks are more diffcult to train. The authors persent a residual learning framework to ease the tr...
Rethinking the Inception Arcitecture for Computer Vision (Inception v2 & v3)Published Year : 2015Paper URL
What
Inception v2 and v3 improved computational efficiency and model accuracy to 3.5% ...
Going deeper with convolutions (Inception, GoogLeNet)Published Year : 2014Paper URL
WhatThis architecture improved utilization of the computing resources inside the network which is achieved by a c...
