AI/Machine Learning Book List

唔夠，要學UG year 1 linear algebra + multivariable calculus + statistics

如果得AS math & stats底其實係咪要由basic algebra學起

起碼要識linear algebra

唔該曬

Thx 巴打

但我意思係上面咁多個範疇應由邊個睇先(我唔想好似未學加數就學乘數咁)
定係每個範疇都可以平行咁睇 無話邊個特別深/淺

先睇statistical inference同convex optimization，前者係打stat底，後者比較易入口
之後好多其他嘅書都係stat theory，大部分可以同時睇
Probability就要識real analysis (measure theory)，可能最難

THX

淨讀theory唔做programming係乜野嘅學AI

跟本兩邊都要學曬先叫識AI

同埋AI數都好多種，淨係用咩optimization咩情況下用乜野loss function都係一大類

淨係做ANN CNN RNN d數都算淺，玩到capsule net 果堆tensorize咗d operator真係

就係programming網上太多resource，呢個post嘅原意就係想希望大家深入了解machine learning，從theory入手，唔係單單為咗學DL，識用下咩tensorflow run下MLP/CNN/RNN/LSTM

而且呢個post唔係focus落deep learning度，如果你講DL用乜optimization同用乜loss function亦都係一啲好皮毛嘅嘢，反而要明白點解某啲optimization algorithms會快啲converge to local minima/易啲escape saddle points先係重點，了解背後原理嘅永遠係少數人，但呢啲少數人先會行得最遠

另外，Machine learning入面applied math同stat嘅theory十分重要，大部分classical algorithms都係由statistics derive，唔係run下program就會學得識

而家有個現象就係DL嘅熱潮加上scikit-learn/tensorflow/pytorch等libraries嘅出現令到入門門檻低咗，但係反而令到初學者有錯覺係識program就等於識ML，而且deep learning只係machine learning嘅一小部分，唔希望有個錯覺識咗DL等於識machine learning，連簡單嘅linear/logistic regression, SVM, Boosting, Bagging, SVM, PCA等等都唔知點運作

linear regression正常讀過大學都應該識嘅嘢嚟，做ml反而唔識嘅話就真係

例子姐，statistical learning其實好博大精深，而且high-dimensional statistics更加同EE/CS關係好密切

我係civil PhD 雖然research同ML冇乜關係，但一直好想學下ML，畢竟係大趨勢！想問下剩係學校Linear Algebra同calculus 夠唔夠讀上面堆書？定要讀其他入門書先？好有心學，唔該巴打先！

其實無乜所謂。好似學電腦咁，分好多層面。你嘅興趣係寫game，你都唔會自己去由operation system 學寫上去，只要大概明白OS有乜function，唔洗去研究implementation detail. 當然，當ML初學者program到某一個階段，對啲library有興趣,咁可以深研一下theory.

好多fields 都係咁樣

Applied Science vs Science
Architects vs Civil Engineers
Traders vs Quants

其實要ML入門的話, 上coursera 已經夠, 部份書上面GE野已經過時
識basic linear algebra, calculus, stat 已經夠做

如果唔滿足只係入門, 而係做research 的話, 就要睇你做邊方面, 如果你想做practical d, 咁可能唔需要太強ge theory 知識

lee 個post 入面D 書都係for ML, AI仲有好多其他野(robotic, planning, scheduling果D) 如果巴打絲打係對其他有興趣就要另外搵書了

香港學背後原理意義唔大
最重要係識用
除非你真係入到Google, Microsoft的Research Team做

如果想commercial application
應該係學呢些
https://academy.microsoft.com/en-us/professional-program/tracks/artificial-intelligence/

AI同ML唔係淨係得DL/ANN一途

但係支撐AI發展除左數學,仲需要software engineering, big data處理

你識好深入ML d數,代唔代表好了解AI/ML?其實都只係睇到其中一層

我既應用係computer vision, CNN, kmeans, histogram分析, bayesian, markov random field, stat分類, spatial registration, feature extraction呢類都玩唔少

做AI有分應用層同純theory層,pure theory係low level d, 應用到coding層面abstraction layer會多左,但兩者係相輔相承

另外做AI而家仲有行chipset一途,你話做AI chipset識唔識linear algebra?佢地一定識
計matrix使唔使識Eigen/MKL/BLAS呢類linear algebra專用library?

你鐘意玩既可以由STL build起自己套ML library,但實戰既時候,TF, caffe, pytorch呢d底層都係用BLAS, LAPACK呢堆野架咋

information theory同physics 某d數都好似

softmax function = Boltzmann statistics
cross entropy就真頭係thermodynamics果度來

所以一開頭已經講左係入門

我係stat底，岩岩睇完ISLR，應該追邊本好？ISLR 入面d數學好似太少，有時仲難理解，例如：PCA

咁直接睇ESL好過

PhD
學埋UG intro Stat就ok