a. 카이검증(교차분석): 명목(범주)형 -> 명목형 자료일 때 사용. 집단 간 비율 비교로 차이가 유의한지 판단하는 분석.
b. t-test(t검증, 차이검증): 명목형 -> 연속형 자료일 때 사용.
2-1.가치함수 어떤 상태에 있으면 얼마의 보상을 받을 것인지에 대한 기대값. 에이전트가 가지고 있는 값으로 직접 다 경험하지 않더라도 보상을 예상. 앞으로 받을 보상은 정책에 따라서 계산되어야함.
벨만 기대 방정식: 계산을 하려면 환경 모델의 확률과 보상을 알아야한다.
2-2. 행동 가치함수( QFunction): 어떤 상태에서 어떤 행동이 얼마나 좋은지 알려줌
3-1. 순차적 행동 결정 문제
3-2.. 다이내믹 프로그래밍 (1953 by 벨만) 큰 문제 안에 작은 문제들이 중첩된 경우 전체 큰 문제를 작은 문제로 쪼개서 풀겠다. 단점 계산을 빠르게 하는 것이지 학습을 하지 않는다. 순차적 문제를 벨만방정식으로 푸는 것.
————————– 1, 2 ——————-
novel: 새로운
fidelity: 충실함, 동등
rationality: 합리성
sufficient: 구현 가능한, 충분한
perceptual: 지각있는
perceive: 인지하다
inference: 추론
priori: 선험적인
vast: 방대한
nondeterministic: 확률값 없이 예측
deliberating: 계획적인, 신중한
utility function: 효용함수
derive: 끌어내다, 유래하다
——– 3 —————-
anomaly: 이상치
supervised
unsupervised
reinforcement learning
exclusive: 배타적인
ambiguous: 모호한
denote: 의미하다
posteriori: 사후
arguably: 틀림없이
typical: 대표적인
nontrivial: 중요한, 자명한
latent: 숨어있는, 잠재된
infer: 결론을 도출하다, 추론하다
reduction: 축소
variability:... read more
주어진 상황에 특화된 해를 찾는데 쓰이는 플래닝 알고리즘으로 그냥 많이 시뮬레이션 해 보고 가장 좋았던 액션을 선택하는 방법. 따라서 다른 상황에서는 재사용이 어렵다.
(1) 지도학습 정책 $\pi_{sl}$
(2) 롤아웃 정책 $\pi_{roll}$
Recently I was reading an article about a cool project that intends to have a neural network create songs of the late club of the 27 (artists that have tragically died at age 27 or near, and in the height of their respective careers), artists such as Amy Winehouse, Jimmy Hendrix, Curt Cobain and Jim Morrison.
The project was created by Over the Bridge, an organization dedicated to increase awareness on mental health and substance abuse in the music industry, trying to denormalize... read more
The omnipresence of technology nowadays has made it commonplace to read news about AI, just a quick glance at today’s headlines, and I get:
Topics from business, manufacturing, supply chain, medicine and biotech and even defense are covered in those news... read more
After many years of a corporate career (17) diverging from computer science, I have now decided to learn Machine Learning and in the process return to coding (something I have always loved!).
To fully grasp the essence of ML I decided to start by coding a ML library myself, so I can fully understand the inner workings, linear algebra and calculus involved in Stochastic Gradient Descent. And on top learn Python (I used to code in C++ 20 years ago).
I built a general purpose basic ML library that... read more
시점 t에서의 밸류와 시점 t+1에서의 밸류 사이의 관계를 다루고 있으며 또 가치 함수와 정책 함수 사이의 관계도 다룸. 무언가 정책이 주어지고, 그 정책을 평가하고 싶을 때 이용.
$v_\pi(s_t) = E_\pi[r_{t+1} + \gamma v_\pi(s_{t+1})]$
$q_\pi(s_t,a_t) = E_{\pi}[r_{t+1} + \gamma q_\pi(s_{t+1},a_{t+1})]$
$v_\pi(s) = \sum\limits_{a\in A} \pi(a|s) q_\pi(s,a) \quad$ 정책이 고정되고 상태 s의 밸류를 계산
$q_\pi(s,a) = r^a_s + \gamma \sum\limits_{s’\in S} P^a_{ss’}v_\pi(s’) \quad$ 액션의 밸류를 평가
4 the seemingly small project I undertook of creating a machine learning neural network that could learn by itself to play tic-tac-toe, I bumped into the necesity of implementing at least one momentum algorithm for the optimization of the network during backpropagation.
And since my original post for the TicTacToe project is quite large already, I decided to post separately these optimization methods and how did I implement them in my code.
Adaptive Moment Estimation (Adam) is an optimization method that computes adaptive learning rates for each weight and bias. In addition to storing an... read more
Recently I was reading an article about a cool project that intends to have a neural network create songs of the late club of the 27 (artists that have tragically died at age 27 or near, and in the height of their respective careers), artists such as Amy Winehouse, Jimmy Hendrix, Curt Cobain and Jim Morrison.
The project was created by Over the Bridge, an organization dedicated to increase awareness on mental health and substance abuse in the music industry, trying to denormalize... read more
Recently I was reading an article about a cool project that intends to have a neural network create songs of the late club of the 27 (artists that have tragically died at age 27 or near, and in the height of their respective careers), artists such as Amy Winehouse, Jimmy Hendrix, Curt Cobain and Jim Morrison.
The project was created by Over the Bridge, an organization dedicated to increase awareness on mental health and substance abuse in the music industry, trying to denormalize... read more
4 the seemingly small project I undertook of creating a machine learning neural network that could learn by itself to play tic-tac-toe, I bumped into the necesity of implementing at least one momentum algorithm for the optimization of the network during backpropagation.
And since my original post for the TicTacToe project is quite large already, I decided to post separately these optimization methods and how did I implement them in my code.
Adaptive Moment Estimation (Adam) is an optimization method that computes adaptive learning rates for each weight and bias. In addition to storing an... read more
For the seemingly small project I undertook of creating a machine learning neural network that could learn by itself to play tic-tac-toe, I bumped into the necesity of implementing at least one momentum algorithm for the optimization of the network during backpropagation.
And since my original post for the TicTacToe project is quite large already, I decided to post separately these optimization methods and how did I implement them in my code.
Adaptive Moment Estimation (Adam) is an optimization method that computes adaptive learning rates for each weight and bias. In addition to storing an... read more
In the midst of a global pandemic caused by the SARS-COV2 coronavirus; I decided to start blogging. I wanted to blog since a long time, I have always enjoyed writing, but many unknowns and having “no time” for it prevented me from taking it up. Things like: “I don’t really know who my target audience is”, “what would my topic or topics be?”, “I don’t think I am a world-class expert in anything”, and many more kept stopping me from setting up my own blog. Now seemed like a good time as any so with those and tons of other... read more
Settings 탭 > Heatmode 콤보박스에서 원하는 히트맵 모드를 선택 
Insatances 탭에서 실험할 환경을 설정하고 체크 버튼을 눌러서 인스턴스를 생성한다. 
여기서는 .xinst 파일만 저장한다. 
Base Controls 탭에서 시작... read more
모델: 대상물을 알기 쉽게 표현하는 것. 다이어그램 모델링: 많은 정보를 간결한 형태로 전달할 수 있고, 오해를 줄일 수 있음.
2. 끼: 성시레 깡:원칙을 지킨다. 끈: 혼자서는 성공할 수 없다. 신세를 지고 나면 꼭 답례와 인사를 한다. 인맥으로 시간 절약 가능 꼴: 표정은 여유롭고 밝게 꿈: 강렬한 꿈
긍정 내기 골프에서 졌을 때 내 돈 보관 잘 하고 있어. 금방 찾아 가루거이까. 요즘 연습... read more
In the midst of a global pandemic caused by the SARS-COV2 coronavirus; I decided to start blogging. I wanted to blog since a long time, I have always enjoyed writing, but many unknowns and having “no time” for it prevented me from taking it up. Things like: “I don’t really know who my target audience is”, “what would my topic or topics be?”, “I don’t think I am a world-class expert in anything”, and many more kept stopping me from setting up my own blog. Now seemed like a good time as any so with those and tons of other... read more
4 the seemingly small project I undertook of creating a machine learning neural network that could learn by itself to play tic-tac-toe, I bumped into the necesity of implementing at least one momentum algorithm for the optimization of the network during backpropagation.
And since my original post for the TicTacToe project is quite large already, I decided to post separately these optimization methods and how did I implement them in my code.
Adaptive Moment Estimation (Adam) is an optimization method that computes adaptive learning rates for each weight and bias. In addition to storing an... read more
Recently I was reading an article about a cool project that intends to have a neural network create songs of the late club of the 27 (artists that have tragically died at age 27 or near, and in the height of their respective careers), artists such as Amy Winehouse, Jimmy Hendrix, Curt Cobain and Jim Morrison.
The project was created by Over the Bridge, an organization dedicated to increase awareness on mental health and substance abuse in the music industry, trying to denormalize... read more
The omnipresence of technology nowadays has made it commonplace to read news about AI, just a quick glance at today’s headlines, and I get:
Topics from business, manufacturing, supply chain, medicine and biotech and even defense are covered in those news... read more
Recently I was reading an article about a cool project that intends to have a neural network create songs of the late club of the 27 (artists that have tragically died at age 27 or near, and in the height of their respective careers), artists such as Amy Winehouse, Jimmy Hendrix, Curt Cobain and Jim Morrison.
The project was created by Over the Bridge, an organization dedicated to increase awareness on mental health and substance abuse in the music industry, trying to denormalize... read more
The omnipresence of technology nowadays has made it commonplace to read news about AI, just a quick glance at today’s headlines, and I get:
Topics from business, manufacturing, supply chain, medicine and biotech and even defense are covered in those news... read more
It must sound crazy that in this day and age, when we have such a myriad of amazing machine learning libraries and toolkits all open sourced, all quite well documented and easy to use, I decided to create my own ML library from scratch.
Let me try to explain; I am in the process of immersing myself into the world of Machine Learning, and to do so, I want to deeply understand the basic concepts and its foundations, and I think that there is no better way to do so than by creating myself all the... read more
4 the seemingly small project I undertook of creating a machine learning neural network that could learn by itself to play tic-tac-toe, I bumped into the necesity of implementing at least one momentum algorithm for the optimization of the network during backpropagation.
And since my original post for the TicTacToe project is quite large already, I decided to post separately these optimization methods and how did I implement them in my code.
Adaptive Moment Estimation (Adam) is an optimization method that computes adaptive learning rates for each weight and bias. In addition to storing an... read more
For the seemingly small project I undertook of creating a machine learning neural network that could learn by itself to play tic-tac-toe, I bumped into the necesity of implementing at least one momentum algorithm for the optimization of the network during backpropagation.
And since my original post for the TicTacToe project is quite large already, I decided to post separately these optimization methods and how did I implement them in my code.
Adaptive Moment Estimation (Adam) is an optimization method that computes adaptive learning rates for each weight and bias. In addition to storing an... read more
After many years of a corporate career (17) diverging from computer science, I have now decided to learn Machine Learning and in the process return to coding (something I have always loved!).
To fully grasp the essence of ML I decided to start by coding a ML library myself, so I can fully understand the inner workings, linear algebra and calculus involved in Stochastic Gradient Descent. And on top learn Python (I used to code in C++ 20 years ago).
I built a general purpose basic ML library that... read more
It must sound crazy that in this day and age, when we have such a myriad of amazing machine learning libraries and toolkits all open sourced, all quite well documented and easy to use, I decided to create my own ML library from scratch.
Let me try to explain; I am in the process of immersing myself into the world of Machine Learning, and to do so, I want to deeply understand the basic concepts and its foundations, and I think that there is no better way to do so than by creating myself all the... read more
I am lately trying to take on coding again. It had always been a part of my life since my early years when I learned to program a Tandy Color Computer at the age of 8, the good old days.
Tandy Color Computer TRS80 III
Having already programed in Java, C# and of course BASIC, I thought it would be a great idea to learn Python since I have great interest in data science and machine learning, and those two topics seem to have an avid community within Python coders.
For one of my starter quick programming... read more
After many years of a corporate career (17) diverging from computer science, I have now decided to learn Machine Learning and in the process return to coding (something I have always loved!).
To fully grasp the essence of ML I decided to start by coding a ML library myself, so I can fully understand the inner workings, linear algebra and calculus involved in Stochastic Gradient Descent. And on top learn Python (I used to code in C++ 20 years ago).
I built a general purpose basic ML library that... read more
flowchart LR i(" 
") -..-> Minimize classDef image fill:none,stroke:none class i image flowchart LR subgraph Inbound direction TB subgraph iw[warehouse] direction TB i[drum] i2[drum] i3[drum3] i4[pallet] i5[pallet] end ex1["Overflow(external storage)"] subgraph "Overflow(external storage)" direction TB dr end subgraph "Overflow(external storage)" direction TB dr2 end iw --> ex1 end orange --> i[drum] --> m[mixer] Mango --> i2[drum] --> m[mixer] vc[Vitamin C] --> i3[drum] --> m[mixer] cl[Carton 1L] --> i4[pallet] --> b[bottle] pb[PET bottle] --> i5[pallet] --> b[bottle] subgraph Product direction TB subgraph mb[Mixing] direction TB m[mixer] end subgraph bb[Bottling] direction TB b[bottle]... read more
1. 구매(Purchasing) : 공급업체 선정, 원자재 구매, 조달관리 책임
agreements
회사 경영이든 시스템 운영이든 초기 레벨에서 최종 성공이나 안정적인 단계까지 도달하기 위해서는 수많은 시행착오가 필요할 것이다
When taking on a major role in a company for the first time, what would one do first? Most likely, unless you’re the owner, you need to show results right away, so the first thing to do would probably be to downsize the workforce. However, downsizing would stir internal resistance.
처음 회사의 중책을 맡게... read more
list
list
α \alpha β \beta γ \gamma δ \delta ϵ \epsilon
ζ \zeta η \eta θ \theta ι \iota κ \kappa
λ \lambda μ \mu ν \nu ξ \xi o o (omicron)
π \pi ρ \rho σ \sigma τ \tau υ \upsilon
ϕ \phi χ \chi ψ \psi ω \omega
ε \varepsilon... read more
For the seemingly small project I undertook of creating a machine learning neural network that could learn by itself to play tic-tac-toe, I bumped into the necesity of implementing at least one momentum algorithm for the optimization of the network during backpropagation.
And since my original post for the TicTacToe project is quite large already, I decided to post separately these optimization methods and how did I implement them in my code.
The Cauchy-Schwarz Inequality $\left( \sum_{k=1}^n a_k b_k \right)^2 \leq \left( \sum_{k=1}^n a_k^2 \right) \left( \sum_{k=1}^n b_k^2 \right)$
Cross entropy loss 식은 $-\frac{1}{n}\sum_{i=1}^n \sum_{c=1}^C... read more
tab을 두번 누르면 위의 백틱(`)을 사용한 것과 같습니다. <span style="color:red">빨간 글씨</span> <span style="color:blue">파란 글씨</span> <span style="color:green">초록 글씨</span> <span style="color:yellow">노란 글씨</span> <span style="color:purple">보라 글씨</span> 각주 : 1 미주 : 1에 대한 내용 미주는 글 뒷 부분에 삽입합니다.
취소선
텍스트 뒤에 space bar를 두번 치고 enter를 누른 뒤 다음 텍스트를 씁니다.
다음
다음
다음 다음
😁 이것은 ==하이라이트== 입니다.
이 태그는 H2O를 표현할 수 있습니다.
일단 실천하라.... read more
In the midst of a global pandemic caused by the SARS-COV2 coronavirus; I decided to start blogging. I wanted to blog since a long time, I have always enjoyed writing, but many unknowns and having “no time” for it prevented me from taking it up. Things like: “I don’t really know who my target audience is”, “what would my topic or topics be?”, “I don’t think I am a world-class expert in anything”, and many more kept stopping me from setting up my own blog. Now seemed like a good time as any so with those and tons of other... read more