- 현재 위치
- home > 컴퓨터·ICT·어학 > 컴퓨터·IT 도서 > 컴퓨터공학 > 인공지능 1[제이펍]
;)
2016년에 나온 제3판 번역서(2009년에 출간된 원서 3판을 번역)는 최신 연구 반영에 한계가 있었으나, 이번 제4판 번역서는 최근 성과(자연어 이해, 로봇공학, 컴퓨터 시각에 심층학습이 끼친 영향, 강화학습을 로봇공학에 적용하는 방법, 기계학습, 인공지능 윤리 등)를 충실하게 반영하였다. ?
저자: 스튜어트 러셀, 피터 노빅 (지은이), 류광 (옮긴이)
PART I 인공지능
CHAPTER 1 소개 3
1.1 인공지능이란 무엇인가? ·············································································· 4
1.2 인공지능의 기반 학문 ··············································································· 10
1.3 인공지능의 역사 ························································································ 25
1.4 인공지능의 현황 ························································································ 38
1.5 인공지능의 위험과 혜택 ············································································ 43
요약 ······································································································ 47
참고문헌 및 역사적 참고사항 ····························································· 49
CHAPTER 2 지능적 에이전트 51
2.1 에이전트와 환경 ························································································ 52
2.2 좋은 행동: 합리성 개념 ············································································ 55
2.3 환경의 본성 ······························································································· 59
2.4 에이전트의 구조 ························································································ 65
요약 ······································································································ 81
참고문헌 및 역사적 참고사항 ····························································· 82
PART II 문제 해결
CHAPTER 3 검색을 통한 문제 해결 87
3.1 문제 해결 에이전트 ··················································································· 88
3.2 문제의 예 ··································································································· 92
3.3 검색 알고리즘들 ························································································ 97
3.4 정보 없는 검색 전략 ··············································································· 104
3.5 정보 있는 검색(발견적 검색) 전략들 ····················································· 114
3.6 발견적 함수 ······························································································ 130
요약 ···································································································· 140
참고문헌 및 역사적 참고사항 ··························································· 141
CHAPTER 4 복잡한 환경의 검색 147
4.1 국소 검색과 최적화 문제 ········································································ 147
4.2 연속 공간의 국소 검색 ············································································ 157
4.3 비결정론적 동작들을 수반한 검색 ·························································· 161
4.4 부분 관측 가능 환경의 검색 ··································································· 167
4.5 온라인 검색 에이전트와 미지 환경 ························································ 177
요약 ···································································································· 185
참고문헌 및 역사적 참고사항 ··························································· 186
CHAPTER 5 대립 검색과 게임 191
5.1 게임 이론 ································································································· 191
5.2 게임의 최적 결정 ····················································································· 194
5.3 발견적 알파베타 트리 검색 ····································································· 203
5.4 몬테카를로 트리 검색 ·············································································· 210
5.5 확률적 게임 ······························································································ 214
5.6 부분 관측 가능 게임 ··············································································· 218
5.7 게임 검색 알고리즘들의 한계 ································································· 224
요약 ···································································································· 226
참고문헌 및 역사적 참고사항 ························································· 227
CHAPTER 6 제약 충족 문제 235
6.1 제약 충족 문제의 정의 ············································································ 236
6.2 제약 전파: CSP의 추론 ·········································································· 242
6.3 CSP를 위한 역추적 검색 ······································································· 250
6.4 CSP를 위한 국소 검색 ··········································································· 257
6.5 문제의 구조 ······························································································ 259
요약 ···································································································· 265
참고문헌 및 역사적 참고사항 ··························································· 266
PART III 지식, 추론, 계획 수립
CHAPTER 7 논리적 에이전트 273
7.1 지식 기반 에이전트 ················································································· 274
7.2 웜퍼스 세계 ······························································································ 276
7.3 논리 ·········································································································· 280
7.4 명제 논리: 아주 간단한 논리 ································································· 284
7.5 명제 정리 증명 ························································································ 291
7.6 효과적인 명제 모형 점검 ········································································ 304
7.7 명제 논리에 기초한 에이전트 ································································· 310
요약 ···································································································· 322
참고문헌 및 역사적 참고사항 ··························································· 323
CHAPTER 8 1차 논리 327
8.1 표현의 재고찰 ·························································································· 327
8.2 1차 논리의 구문과 의미론 ······································································· 333
8.3 1차 논리의 활용 ······················································································· 346
8.4 1차 논리의 지식 공학 ·············································································· 354
요약 ···································································································· 361
참고문헌 및 역사적 참고사항 ··························································· 362
CHAPTER 9 1차 논리의 추론 365
9.1 명제 추론 대 1차 추론 ············································································ 365
9.2 단일화와 1차 추론 ··················································································· 368
9.3 순방향 연쇄 ······························································································ 374
9.4 역방향 연쇄 ······························································································ 382
9.5 분해 ·········································································································· 389
요약 ···································································································· 403
참고문헌 및 역사적 참고사항 ··························································· 404
CHAPTER 10 지식 표현 409
10.1 온톨로지 공학 ························································································ 410
10.2 범주와 객체 ···························································································· 413
10.3 사건 ········································································································ 420
10.4 정신적 객체와 양상 논리 ······································································ 425
10.5 범주 추론 시스템 ··················································································· 429
10.6 기본 정보를 이용한 추론 ······································································ 434
요약 ·································································································· 440
참고문헌 및 역사적 참고사항 ························································· 441
CHAPTER 11 자동 계획 수립 449
11.1 고전적 계획 수립의 정의 ······································································ 450
11.2 고전적 계획 수립을 위한 알고리즘들 ··················································· 455
11.3 계획 수립을 위한 발견적 함수 ····························································· 460
11.4 위계적 계획 수립 ··················································································· 465
11.5 비결정론적 정의역에서의 계획 수립과 실행 ········································ 476
11.6 시간, 일정, 자원 ···················································································· 488
11.7 계획 수립 접근방식들의 분석 ······························································· 493
요약 ·································································································· 494
참고문헌 및 역사적 참고사항 ························································· 495
PART IV 불확실한 지식과 추론
CHAPTER 12 불확실성의 정량화 505
12.1 불확실성하에서의 행동 ·········································································· 505
12.2 기본적인 확률 표기법 ············································································ 510
12.3 완전 결합 분포를 이용한 추론 ····························································· 518
12.4 독립성 ····································································································· 522
12.5 베이즈 규칙과 그 용법 ·········································································· 523
12.6 단순 베이즈 모형 ··················································································· 528
12.7 웜퍼스 세계의 재고찰 ············································································ 530
요약 ·································································································· 534
참고문헌 및 역사적 참고사항 ························································· 535
CHAPTER 13 확률적 추론 539
13.1 불확실한 문제 영역의 지식 표현 ·························································· 539
13.2 베이즈망의 의미론 ················································································· 542
13.3 베이즈망의 정확 추론 ············································································ 558
13.4 베이즈망의 근사 추론 ············································································ 568
13.5 인과망 ····································································································· 585
요약 ·································································································· 591
참고문헌 및 역사적 참고사항 ························································· 591
CHAPTER 14 시간에 따른 확률적 추론 599
14.1 시간과 불확실성 ····················································································· 600
14.2 시간적 모형의 추론 ··············································································· 605
14.3 은닉 마르코프 모형 ··············································································· 615
14.4 칼만 필터 ······························································································· 622
14.5 동적 베이즈망 ························································································ 630
요약 ·································································································· 643
참고문헌 및 역사적 참고사항 ························································· 644
CHAPTER 15 확률적 프로그래밍 647
15.1 관계 확률 모형 ······················································································ 648
15.2 열린 모집단 확률 모형 ·········································································· 656
15.3 복잡한 세계의 추적 ··············································································· 665
15.4 확률 모형으로서의 프로그램 ································································· 670
요약 ·································································································· 676
참고문헌 및 역사적 참고사항 ························································· 676
CHAPTER 16 간단한 의사결정 683
16.1 불확실성하에서의 믿음과 욕구의 결합 ················································· 684
16.2 효용이론의 기초 ····················································································· 685
16.3 효용 함수 ······························································································· 689
16.4 다중 특성 효용 함수 ············································································· 699
16.5 의사결정망 ······························································································ 705
16.6 정보의 가치 ···························································································· 708
16.7 미지의 선호도 ························································································ 716
요약 ·································································································· 720
참고문헌 및 역사적 참고사항 ························································· 721
CHAPTER 17 복잡한 의사결정 727
17.1 순차적 의사결정 문제 ············································································ 727
17.2 MDP를 위한 알고리즘들 ······································································· 740
17.3 강도 문제 ······························································································· 750
17.4 부분 관측 가능 MDP ············································································ 759
17.5 POMDP를 푸는 알고리즘 ····································································· 762
요약 ·································································································· 768
참고문헌 및 역사적 참고사항 ························································· 769
CHAPTER 18 다중 에이전트 의사결정 775
18.1 다중 에이전트 환경의 특징 ··································································· 775
18.2 비협력 게임 이론 ··················································································· 783
18.3 협력 게임 이론 ······················································································ 809
18.4 집합적 의사결정 ····················································································· 818
요약 ·································································································· 835
참고문헌 및 역사적 참고사항 ························································· 836
찾아보기 ·················································· 843
CHAPTER 1 소개 3
1.1 인공지능이란 무엇인가? ·············································································· 4
1.2 인공지능의 기반 학문 ··············································································· 10
1.3 인공지능의 역사 ························································································ 25
1.4 인공지능의 현황 ························································································ 38
1.5 인공지능의 위험과 혜택 ············································································ 43
요약 ······································································································ 47
참고문헌 및 역사적 참고사항 ····························································· 49
CHAPTER 2 지능적 에이전트 51
2.1 에이전트와 환경 ························································································ 52
2.2 좋은 행동: 합리성 개념 ············································································ 55
2.3 환경의 본성 ······························································································· 59
2.4 에이전트의 구조 ························································································ 65
요약 ······································································································ 81
참고문헌 및 역사적 참고사항 ····························································· 82
PART II 문제 해결
CHAPTER 3 검색을 통한 문제 해결 87
3.1 문제 해결 에이전트 ··················································································· 88
3.2 문제의 예 ··································································································· 92
3.3 검색 알고리즘들 ························································································ 97
3.4 정보 없는 검색 전략 ··············································································· 104
3.5 정보 있는 검색(발견적 검색) 전략들 ····················································· 114
3.6 발견적 함수 ······························································································ 130
요약 ···································································································· 140
참고문헌 및 역사적 참고사항 ··························································· 141
CHAPTER 4 복잡한 환경의 검색 147
4.1 국소 검색과 최적화 문제 ········································································ 147
4.2 연속 공간의 국소 검색 ············································································ 157
4.3 비결정론적 동작들을 수반한 검색 ·························································· 161
4.4 부분 관측 가능 환경의 검색 ··································································· 167
4.5 온라인 검색 에이전트와 미지 환경 ························································ 177
요약 ···································································································· 185
참고문헌 및 역사적 참고사항 ··························································· 186
CHAPTER 5 대립 검색과 게임 191
5.1 게임 이론 ································································································· 191
5.2 게임의 최적 결정 ····················································································· 194
5.3 발견적 알파베타 트리 검색 ····································································· 203
5.4 몬테카를로 트리 검색 ·············································································· 210
5.5 확률적 게임 ······························································································ 214
5.6 부분 관측 가능 게임 ··············································································· 218
5.7 게임 검색 알고리즘들의 한계 ································································· 224
요약 ···································································································· 226
참고문헌 및 역사적 참고사항 ························································· 227
CHAPTER 6 제약 충족 문제 235
6.1 제약 충족 문제의 정의 ············································································ 236
6.2 제약 전파: CSP의 추론 ·········································································· 242
6.3 CSP를 위한 역추적 검색 ······································································· 250
6.4 CSP를 위한 국소 검색 ··········································································· 257
6.5 문제의 구조 ······························································································ 259
요약 ···································································································· 265
참고문헌 및 역사적 참고사항 ··························································· 266
PART III 지식, 추론, 계획 수립
CHAPTER 7 논리적 에이전트 273
7.1 지식 기반 에이전트 ················································································· 274
7.2 웜퍼스 세계 ······························································································ 276
7.3 논리 ·········································································································· 280
7.4 명제 논리: 아주 간단한 논리 ································································· 284
7.5 명제 정리 증명 ························································································ 291
7.6 효과적인 명제 모형 점검 ········································································ 304
7.7 명제 논리에 기초한 에이전트 ································································· 310
요약 ···································································································· 322
참고문헌 및 역사적 참고사항 ··························································· 323
CHAPTER 8 1차 논리 327
8.1 표현의 재고찰 ·························································································· 327
8.2 1차 논리의 구문과 의미론 ······································································· 333
8.3 1차 논리의 활용 ······················································································· 346
8.4 1차 논리의 지식 공학 ·············································································· 354
요약 ···································································································· 361
참고문헌 및 역사적 참고사항 ··························································· 362
CHAPTER 9 1차 논리의 추론 365
9.1 명제 추론 대 1차 추론 ············································································ 365
9.2 단일화와 1차 추론 ··················································································· 368
9.3 순방향 연쇄 ······························································································ 374
9.4 역방향 연쇄 ······························································································ 382
9.5 분해 ·········································································································· 389
요약 ···································································································· 403
참고문헌 및 역사적 참고사항 ··························································· 404
CHAPTER 10 지식 표현 409
10.1 온톨로지 공학 ························································································ 410
10.2 범주와 객체 ···························································································· 413
10.3 사건 ········································································································ 420
10.4 정신적 객체와 양상 논리 ······································································ 425
10.5 범주 추론 시스템 ··················································································· 429
10.6 기본 정보를 이용한 추론 ······································································ 434
요약 ·································································································· 440
참고문헌 및 역사적 참고사항 ························································· 441
CHAPTER 11 자동 계획 수립 449
11.1 고전적 계획 수립의 정의 ······································································ 450
11.2 고전적 계획 수립을 위한 알고리즘들 ··················································· 455
11.3 계획 수립을 위한 발견적 함수 ····························································· 460
11.4 위계적 계획 수립 ··················································································· 465
11.5 비결정론적 정의역에서의 계획 수립과 실행 ········································ 476
11.6 시간, 일정, 자원 ···················································································· 488
11.7 계획 수립 접근방식들의 분석 ······························································· 493
요약 ·································································································· 494
참고문헌 및 역사적 참고사항 ························································· 495
PART IV 불확실한 지식과 추론
CHAPTER 12 불확실성의 정량화 505
12.1 불확실성하에서의 행동 ·········································································· 505
12.2 기본적인 확률 표기법 ············································································ 510
12.3 완전 결합 분포를 이용한 추론 ····························································· 518
12.4 독립성 ····································································································· 522
12.5 베이즈 규칙과 그 용법 ·········································································· 523
12.6 단순 베이즈 모형 ··················································································· 528
12.7 웜퍼스 세계의 재고찰 ············································································ 530
요약 ·································································································· 534
참고문헌 및 역사적 참고사항 ························································· 535
CHAPTER 13 확률적 추론 539
13.1 불확실한 문제 영역의 지식 표현 ·························································· 539
13.2 베이즈망의 의미론 ················································································· 542
13.3 베이즈망의 정확 추론 ············································································ 558
13.4 베이즈망의 근사 추론 ············································································ 568
13.5 인과망 ····································································································· 585
요약 ·································································································· 591
참고문헌 및 역사적 참고사항 ························································· 591
CHAPTER 14 시간에 따른 확률적 추론 599
14.1 시간과 불확실성 ····················································································· 600
14.2 시간적 모형의 추론 ··············································································· 605
14.3 은닉 마르코프 모형 ··············································································· 615
14.4 칼만 필터 ······························································································· 622
14.5 동적 베이즈망 ························································································ 630
요약 ·································································································· 643
참고문헌 및 역사적 참고사항 ························································· 644
CHAPTER 15 확률적 프로그래밍 647
15.1 관계 확률 모형 ······················································································ 648
15.2 열린 모집단 확률 모형 ·········································································· 656
15.3 복잡한 세계의 추적 ··············································································· 665
15.4 확률 모형으로서의 프로그램 ································································· 670
요약 ·································································································· 676
참고문헌 및 역사적 참고사항 ························································· 676
CHAPTER 16 간단한 의사결정 683
16.1 불확실성하에서의 믿음과 욕구의 결합 ················································· 684
16.2 효용이론의 기초 ····················································································· 685
16.3 효용 함수 ······························································································· 689
16.4 다중 특성 효용 함수 ············································································· 699
16.5 의사결정망 ······························································································ 705
16.6 정보의 가치 ···························································································· 708
16.7 미지의 선호도 ························································································ 716
요약 ·································································································· 720
참고문헌 및 역사적 참고사항 ························································· 721
CHAPTER 17 복잡한 의사결정 727
17.1 순차적 의사결정 문제 ············································································ 727
17.2 MDP를 위한 알고리즘들 ······································································· 740
17.3 강도 문제 ······························································································· 750
17.4 부분 관측 가능 MDP ············································································ 759
17.5 POMDP를 푸는 알고리즘 ····································································· 762
요약 ·································································································· 768
참고문헌 및 역사적 참고사항 ························································· 769
CHAPTER 18 다중 에이전트 의사결정 775
18.1 다중 에이전트 환경의 특징 ··································································· 775
18.2 비협력 게임 이론 ··················································································· 783
18.3 협력 게임 이론 ······················································································ 809
18.4 집합적 의사결정 ····················································································· 818
요약 ·································································································· 835
참고문헌 및 역사적 참고사항 ························································· 836
찾아보기 ·················································· 843
2010년대 인공신경망의 부활과 심층학습의 눈부신 성과를 반영한 인공지능 연구의 결정판!
2016년에 나온 제3판 번역서(2009년에 출간된 원서 3판을 번역)는 최신 연구 반영에 한계가 있었으나, 이번 제4판 번역서는 최근 성과(자연어 이해, 로봇공학, 컴퓨터 시각에 심층학습이 끼친 영향, 강화학습을 로봇공학에 적용하는 방법, 기계학습, 인공지능 윤리 등)를 충실하게 반영한, 2020년에 출간된 원서를 옮긴 것이라 이 분야의 ‘좀 더 통합된 상’을 원하는 여러 독자의 갈증을 해소하는 데 큰 도움이 될 것입니다.
전체적으로, 책의 약 25%가 완전히 새로운 내용이고 나머지 75%도 이 분야의 좀 더 통합된 상을 제시하기 위해 크게 변경되었으며, 이번 판에서 인용한 문헌의 22%는 2010년 이후에 출판된 것들입니다.
제4판에서 새로운 점들
□ 사람이 손으로 짜는 지식 공학보다는 기계학습에 좀 더 무게를 실었다. 기계학습은 가용 데이터와 컴퓨팅 자원이 증가하고 새로운 알고리즘들이 등장한 덕분에 큰 성공을 거두고 있다.
□ 심층학습, 확률적 프로그래밍, 다중 에이전트 시스템을 각각 개별적인 장(챕터)으로 두어서 좀 더 자세히 다룬다.
□ 자연어 이해, 로봇공학, 컴퓨터 시각에 관한 장들을 심층학습이 끼친 영향을 반영해서 수정했다.
□ 로봇공학 장에 사람과 상호작용하는 로봇에 관한 내용과 강화학습을 로봇공학에 적용하는 방법에 관한 내용이 추가되었다.
□ 이전에는 인공지능의 목표를 사람이 구체적인 효용 정보(목적함수)를 제공한다는 가정하에서 기대 효용을 최대화하려는 시스템을 만드는 것이라고 정의했다. 그러나 이번 판에서는 목적함수가 고정되어 있으며 인공지능 시스템이 목적함수를 알고 있다고 가정하지 않는다. 대신, 시스템은 자신이 봉사하는 인간의 진짜 목적이 무엇인지 확실하게 알지 못할 수 있다고 가정한다. 시스템은 반드시 자신이 무엇을 최대화할 것인지를 배워야 하며, 목적에 관해 불확실성이 존재하더라도 적절히 작동해야 한다.
□ 인공지능이 사회에 미치는 영향을 좀 더 자세하게 다루었다. 여기에는 윤리, 공정성, 신뢰, 안정성에 관한 핵심적인 문제들을 고찰한다.
□ 각 장 끝의 연습문제들을 온라인 사이트로 옮겼다. 덕분에 강사들의 요구와 이 분야 및 인공지능 관련 소프트웨어 도구의 발전에 맞게 연습문제들을 계속 추가, 갱신, 개선할 수 있게 되었다.
2016년에 나온 제3판 번역서(2009년에 출간된 원서 3판을 번역)는 최신 연구 반영에 한계가 있었으나, 이번 제4판 번역서는 최근 성과(자연어 이해, 로봇공학, 컴퓨터 시각에 심층학습이 끼친 영향, 강화학습을 로봇공학에 적용하는 방법, 기계학습, 인공지능 윤리 등)를 충실하게 반영한, 2020년에 출간된 원서를 옮긴 것이라 이 분야의 ‘좀 더 통합된 상’을 원하는 여러 독자의 갈증을 해소하는 데 큰 도움이 될 것입니다.
전체적으로, 책의 약 25%가 완전히 새로운 내용이고 나머지 75%도 이 분야의 좀 더 통합된 상을 제시하기 위해 크게 변경되었으며, 이번 판에서 인용한 문헌의 22%는 2010년 이후에 출판된 것들입니다.
제4판에서 새로운 점들
□ 사람이 손으로 짜는 지식 공학보다는 기계학습에 좀 더 무게를 실었다. 기계학습은 가용 데이터와 컴퓨팅 자원이 증가하고 새로운 알고리즘들이 등장한 덕분에 큰 성공을 거두고 있다.
□ 심층학습, 확률적 프로그래밍, 다중 에이전트 시스템을 각각 개별적인 장(챕터)으로 두어서 좀 더 자세히 다룬다.
□ 자연어 이해, 로봇공학, 컴퓨터 시각에 관한 장들을 심층학습이 끼친 영향을 반영해서 수정했다.
□ 로봇공학 장에 사람과 상호작용하는 로봇에 관한 내용과 강화학습을 로봇공학에 적용하는 방법에 관한 내용이 추가되었다.
□ 이전에는 인공지능의 목표를 사람이 구체적인 효용 정보(목적함수)를 제공한다는 가정하에서 기대 효용을 최대화하려는 시스템을 만드는 것이라고 정의했다. 그러나 이번 판에서는 목적함수가 고정되어 있으며 인공지능 시스템이 목적함수를 알고 있다고 가정하지 않는다. 대신, 시스템은 자신이 봉사하는 인간의 진짜 목적이 무엇인지 확실하게 알지 못할 수 있다고 가정한다. 시스템은 반드시 자신이 무엇을 최대화할 것인지를 배워야 하며, 목적에 관해 불확실성이 존재하더라도 적절히 작동해야 한다.
□ 인공지능이 사회에 미치는 영향을 좀 더 자세하게 다루었다. 여기에는 윤리, 공정성, 신뢰, 안정성에 관한 핵심적인 문제들을 고찰한다.
□ 각 장 끝의 연습문제들을 온라인 사이트로 옮겼다. 덕분에 강사들의 요구와 이 분야 및 인공지능 관련 소프트웨어 도구의 발전에 맞게 연습문제들을 계속 추가, 갱신, 개선할 수 있게 되었다.
