Deep Learning Book Ian Goodfellow All Chapters Instant Download
Deep Learning Book Ian Goodfellow All Chapters Instant Download
com
https://textbookfull.com/product/deep-learning-book-ian-
goodfellow/
OR CLICK BUTTON
DOWNLOAD NOW
https://textbookfull.com/product/deep-learning-on-windows-building-
deep-learning-computer-vision-systems-on-microsoft-windows-thimira-
amaratunga/
textboxfull.com
https://textbookfull.com/product/deep-learning-pipeline-building-a-
deep-learning-model-with-tensorflow-1st-edition-hisham-el-amir/
textboxfull.com
https://textbookfull.com/product/deep-learning-with-python-develop-
deep-learning-models-on-theano-and-tensorflow-using-keras-jason-
brownlee/
textboxfull.com
Deep Learning for Natural Language Processing Develop Deep
Learning Models for Natural Language in Python Jason
Brownlee
https://textbookfull.com/product/deep-learning-for-natural-language-
processing-develop-deep-learning-models-for-natural-language-in-
python-jason-brownlee/
textboxfull.com
https://textbookfull.com/product/deep-learning-in-natural-language-
processing-deng/
textboxfull.com
https://textbookfull.com/product/deep-learning-for-cancer-diagnosis-
utku-kose/
textboxfull.com
https://textbookfull.com/product/r-deep-learning-essentials-1st-
edition-wiley/
textboxfull.com
Deep Learning
Ian Goodfellow
Yoshua Bengio
Aaron Courville
Contents
Website viii
Acknowledgments ix
Notation xiii
1 Introduction 1
1.1 Who Should Read This Book? . . . . . . . . . . . . . . . . . . . . 8
1.2 Historical Trends in Deep Learning . . . . . . . . . . . . . . . . . 12
2 Linear Algebra 29
2.1 Scalars, Vectors, Matrices and Tensors . . . . . . . . . . . . . . . 29
2.2 Multiplying Matrices and Vectors . . . . . . . . . . . . . . . . . . 32
2.3 Identity and Inverse Matrices . . . . . . . . . . . . . . . . . . . . 34
2.4 Linear Dependence and Span . . . . . . . . . . . . . . . . . . . . 35
2.5 Norms . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 37
2.6 Special Kinds of Matrices and Vectors . . . . . . . . . . . . . . . 38
2.7 Eigendecomposition . . . . . . . . . . . . . . . . . . . . . . . . . . 40
2.8 Singular Value Decomposition . . . . . . . . . . . . . . . . . . . . 42
2.9 The Moore-Penrose Pseudoinverse . . . . . . . . . . . . . . . . . . 43
2.10 The Trace Operator . . . . . . . . . . . . . . . . . . . . . . . . . 44
2.11 The Determinant . . . . . . . . . . . . . . . . . . . . . . . . . . . 45
2.12 Example: Principal Components Analysis . . . . . . . . . . . . . 45
i
CONTENTS
4 Numerical Computation 78
4.1 Overflow and Underflow . . . . . . . . . . . . . . . . . . . . . . . 78
4.2 Poor Conditioning . . . . . . . . . . . . . . . . . . . . . . . . . . 80
4.3 Gradient-Based Optimization . . . . . . . . . . . . . . . . . . . . 80
4.4 Constrained Optimization . . . . . . . . . . . . . . . . . . . . . . 91
4.5 Example: Linear Least Squares . . . . . . . . . . . . . . . . . . . 94
ii
CONTENTS
12 Applications 438
12.1 Large-Scale Deep Learning . . . . . . . . . . . . . . . . . . . . . . 438
12.2 Computer Vision . . . . . . . . . . . . . . . . . . . . . . . . . . . 447
12.3 Speech Recognition . . . . . . . . . . . . . . . . . . . . . . . . . . 453
12.4 Natural Language Processing . . . . . . . . . . . . . . . . . . . . 456
12.5 Other Applications . . . . . . . . . . . . . . . . . . . . . . . . . . 473
iv
CONTENTS
14 Autoencoders 499
14.1 Undercomplete Autoencoders . . . . . . . . . . . . . . . . . . . . 500
14.2 Regularized Autoencoders . . . . . . . . . . . . . . . . . . . . . . 501
14.3 Representational Power, Layer Size and Depth . . . . . . . . . . . 505
14.4 Stochastic Encoders and Decoders . . . . . . . . . . . . . . . . . . 506
14.5 Denoising Autoencoders . . . . . . . . . . . . . . . . . . . . . . . 507
14.6 Learning Manifolds with Autoencoders . . . . . . . . . . . . . . . 513
14.7 Contractive Autoencoders . . . . . . . . . . . . . . . . . . . . . . 518
14.8 Predictive Sparse Decomposition . . . . . . . . . . . . . . . . . . 521
14.9 Applications of Autoencoders . . . . . . . . . . . . . . . . . . . . 522
v
CONTENTS
Bibliography 717
vi
CONTENTS
Index 773
vii
Website
www.deeplearningbook.org
viii
Acknowledgments
This book would not have been possible without the contributions of many people.
We would like to thank those who commented on our proposal for the book
and helped plan its contents and organization: Guillaume Alain, Kyunghyun Cho,
Çağlar Gülçehre, David Krueger, Hugo Larochelle, Razvan Pascanu and Thomas
Rohée.
We would like to thank the people who offered feedback on the content of the
book itself. Some offered feedback on many chapters: Martín Abadi, Ishaq Aden-Ali,
Guillaume Alain, Ion Androutsopoulos, Laura Ball, Fred Bertsch, Olexa Bilaniuk,
Ufuk Can Biçici, Matko Bošnjak, John Boersma, François Brault, Greg Brockman,
Alexandre de Brébisson, Pierre Luc Carrier, Sarath Chandar, Pawel Chilinski,
Mark Daoust, Oleg Dashevskii, Laurent Dinh, Stephan Dreseitl, Gudmundur
Einarsson, Hannes von Essen, Jim Fan, Miao Fan, Meire Fortunato, Frédéric
Francis, Nando de Freitas, Çağlar Gülçehre, Jurgen Van Gael, Yaroslav Ganin,
Javier Alonso García, Aydin Gerek, Stefan Heil, Jonathan Hunt, Gopi Jeyaram,
Chingiz Kabytayev, Lukasz Kaiser, Varun Kanade, Asifullah Khan, Akiel Khan,
John King, Diederik P. Kingma, Dominik Laupheimer, Yann LeCun, Minh Lê, Max
Marion, Rudolf Mathey, Matías Mattamala, Abhinav Maurya, Vincent Michalski,
Kevin Murphy, Oleg Mürk, Hung Ngo, Roman Novak, Augustus Q. Odena, Simon
Pavlik, Karl Pichotta, Eddie Pierce, Kari Pulli, Roussel Rahman, Tapani Raiko,
Anurag Ranjan, Johannes Roith, Mihaela Rosca, Halis Sak, César Salgado, Grigory
Sapunov, Yoshinori Sasaki, Mike Schuster, Julian Serban, Nir Shabat, Ken Shirriff,
Andre Simpelo, Scott Stanley, David Sussillo, Ilya Sutskever, Carles Gelada Sáez,
Graham Taylor, Valentin Tolmer, Massimiliano Tomassoli, An Tran, Shubhendu
Trivedi, Alexey Umnov, Vincent Vanhoucke, Robert Viragh, Marco Visentini-
Scarzanella, Martin Vita, David Warde-Farley, Dustin Webb, Shan-Conrad Wolf,
Kelvin Xu, Wei Xue, Ke Yang, Li Yao, Zygmunt Zając and Ozan Çağlayan.
We would also like to thank those who provided us with useful feedback on
individual chapters:
ix
CONTENTS
• Chapter 16, Structured Probabilistic Models for Deep Learning: Deng Qingyu
, Harry Braviner, Timothy Cogan, Diego Marez, Anton Varfolom and Victor
Xie.
• Chapter 18, Confronting the Partition Function: Sam Bowman and Jin Kim.
book and receive feedback and guidance from colleagues. We would especially like
to thank Ian’s former manager, Greg Corrado, and his current manager, Samy
Bengio, for their support of this project. Finally, we would like to thank Geoffrey
Hinton for encouragement when writing was difficult.
xii
Notation
This section provides a concise reference describing the notation used throughout
this book. If you are unfamiliar with any of the corresponding mathematical
concepts, we describe most of these ideas in chapters 2–4.
xiii
CONTENTS
Indexing
ai Element i of vector a , with indexing starting at 1
a−i All elements of vector a except for element i
Ai,j Element i, j of matrix A
Ai,: Row i of matrix A
A:,i Column i of matrix A
Ai,j,k Element (i, j, k ) of a 3-D tensor A
A :,:,i 2-D slice of a 3-D tensor
ai Element i of the random vector a
xiv
CONTENTS
Calculus
dy
Derivative of y with respect to x
dx
∂y
Partial derivative of y with respect to x
∂x
∇ xy Gradient of y with respect to x
∇X y Matrix derivatives of y with respect to X
∇ Xy Tensor containing derivatives of y with respect to
X
∂f
Jacobian matrix J ∈ Rm×n of f : Rn → Rm
∂x
2
∇x f (x) or H (f )(x) The Hessian matrix of f at input point x
f (x)dx Definite integral over the entire domain of x
f (x)dx Definite integral with respect to x over the set S
S
xv
CONTENTS
Functions
f :A→B The function f with domain A and range B
f ◦g Composition of the functions f and g
f (x; θ) A function of x parametrized by θ. (Sometimes
we write f(x) and omit the argument θ to lighten
notation)
log x Natural logarithm of x
1
σ(x) Logistic sigmoid,
1 + exp(−x)
ζ (x) Softplus, log(1 + exp(x))
||x||p Lp norm of x
||x|| L2 norm of x
x+ Positive part of x, i.e., max(0, x)
1 condition is 1 if the condition is true, 0 otherwise
Sometimes we use a function f whose argument is a scalar but apply it to a
vector, matrix, or tensor: f (x), f(X ), or f (X ). This denotes the application of f
to the array element-wise. For example, if C = σ(X ), then C i,j,k = σ(Xi,j,k ) for all
valid values of i, j and k.
xvi
Chapter 1
Introduction
Inventors have long dreamed of creating machines that think. This desire dates
back to at least the time of ancient Greece. The mythical figures Pygmalion,
Daedalus, and Hephaestus may all be interpreted as legendary inventors, and
Galatea, Talos, and Pandora may all be regarded as artificial life (Ovid and Martin,
2004; Sparkes, 1996; Tandy, 1997).
When programmable computers were first conceived, people wondered whether
such machines might become intelligent, over a hundred years before one was
built (Lovelace, 1842). Today, artificial intelligence (AI) is a thriving field with
many practical applications and active research topics. We look to intelligent
software to automate routine labor, understand speech or images, make diagnoses
in medicine and support basic scientific research.
In the early days of artificial intelligence, the field rapidly tackled and solved
problems that are intellectually difficult for human beings but relatively straight-
forward for computers—problems that can be described by a list of formal, math-
ematical rules. The true challenge to artificial intelligence proved to be solving
the tasks that are easy for people to perform but hard for people to describe
formally—problems that we solve intuitively, that feel automatic, like recognizing
spoken words or faces in images.
This book is about a solution to these more intuitive problems. This solution is
to allow computers to learn from experience and understand the world in terms of
a hierarchy of concepts, with each concept defined through its relation to simpler
concepts. By gathering knowledge from experience, this approach avoids the need
for human operators to formally specify all the knowledge that the computer needs.
The hierarchy of concepts enables the computer to learn complicated concepts by
building them out of simpler ones. If we draw a graph showing how these concepts
1
CHAPTER 1. INTRODUCTION
are built on top of each other, the graph is deep, with many layers. For this reason,
we call this approach to AI deep learning.
Many of the early successes of AI took place in relatively sterile and formal
environments and did not require computers to have much knowledge about
the world. For example, IBM’s Deep Blue chess-playing system defeated world
champion Garry Kasparov in 1997 (Hsu, 2002). Chess is of course a very simple
world, containing only sixty-four locations and thirty-two pieces that can move
in only rigidly circumscribed ways. Devising a successful chess strategy is a
tremendous accomplishment, but the challenge is not due to the difficulty of
describing the set of chess pieces and allowable moves to the computer. Chess
can be completely described by a very brief list of completely formal rules, easily
provided ahead of time by the programmer.
Ironically, abstract and formal tasks that are among the most difficult mental
undertakings for a human being are among the easiest for a computer. Computers
have long been able to defeat even the best human chess player but only recently
have begun matching some of the abilities of average human beings to recognize
objects or speech. A person’s everyday life requires an immense amount of
knowledge about the world. Much of this knowledge is subjective and intuitive,
and therefore difficult to articulate in a formal way. Computers need to capture
this same knowledge in order to behave in an intelligent way. One of the key
challenges in artificial intelligence is how to get this informal knowledge into a
computer.
Several artificial intelligence projects have sought to hard-code knowledge
about the world in formal languages. A computer can reason automatically about
statements in these formal languages using logical inference rules. This is known as
the knowledge base approach to artificial intelligence. None of these projects has
led to a major success. One of the most famous such projects is Cyc (Lenat and
Guha, 1989). Cyc is an inference engine and a database of statements in a language
called CycL. These statements are entered by a staff of human supervisors. It is an
unwieldy process. People struggle to devise formal rules with enough complexity
to accurately describe the world. For example, Cyc failed to understand a story
about a person named Fred shaving in the morning (Linde, 1992). Its inference
engine detected an inconsistency in the story: it knew that people do not have
electrical parts, but because Fred was holding an electric razor, it believed the
entity “FredWhileShaving” contained electrical parts. It therefore asked whether
Fred was still a person while he was shaving.
The difficulties faced by systems relying on hard-coded knowledge suggest
that AI systems need the ability to acquire their own knowledge, by extracting
2
CHAPTER 1. INTRODUCTION
patterns from raw data. This capability is known as machine learning. The
introduction of machine learning enabled computers to tackle problems involving
knowledge of the real world and make decisions that appear subjective. A simple
machine learning algorithm called logistic regression can determine whether to
recommend cesarean delivery (Mor-Yosef et al., 1990). A simple machine learning
algorithm called naive Bayes can separate legitimate e-mail from spam e-mail.
The performance of these simple machine learning algorithms depends heavily
on the representation of the data they are given. For example, when logistic
regression is used to recommend cesarean delivery, the AI system does not examine
the patient directly. Instead, the doctor tells the system several pieces of relevant
information, such as the presence or absence of a uterine scar. Each piece of
information included in the representation of the patient is known as a feature.
Logistic regression learns how each of these features of the patient correlates with
various outcomes. However, it cannot influence how features are defined in any
way. If logistic regression were given an MRI scan of the patient, rather than
the doctor’s formalized report, it would not be able to make useful predictions.
Individual pixels in an MRI scan have negligible correlation with any complications
that might occur during delivery.
This dependence on representations is a general phenomenon that appears
throughout computer science and even daily life. In computer science, operations
such as searching a collection of data can proceed exponentially faster if the collec-
tion is structured and indexed intelligently. People can easily perform arithmetic
on Arabic numerals but find arithmetic on Roman numerals much more time
consuming. It is not surprising that the choice of representation has an enormous
effect on the performance of machine learning algorithms. For a simple visual
example, see figure 1.1.
Many artificial intelligence tasks can be solved by designing the right set of
features to extract for that task, then providing these features to a simple machine
learning algorithm. For example, a useful feature for speaker identification from
sound is an estimate of the size of the speaker’s vocal tract. This feature gives a
strong clue as to whether the speaker is a man, woman, or child.
For many tasks, however, it is difficult to know what features should be
extracted. For example, suppose that we would like to write a program to detect
cars in photographs. We know that cars have wheels, so we might like to use the
presence of a wheel as a feature. Unfortunately, it is difficult to describe exactly
what a wheel looks like in terms of pixel values. A wheel has a simple geometric
shape, but its image may be complicated by shadows falling on the wheel, the sun
glaring off the metal parts of the wheel, the fender of the car or an object in the
3
CHAPTER 1. INTRODUCTION
4
CHAPTER 1. INTRODUCTION
context, we use the word “factors” simply to refer to separate sources of influence;
the factors are usually not combined by multiplication. Such factors are often not
quantities that are directly observed. Instead, they may exist as either unobserved
objects or unobserved forces in the physical world that affect observable quantities.
They may also exist as constructs in the human mind that provide useful simplifying
explanations or inferred causes of the observed data. They can be thought of as
concepts or abstractions that help us make sense of the rich variability in the data.
When analyzing a speech recording, the factors of variation include the speaker’s
age, their sex, their accent and the words they are speaking. When analyzing an
image of a car, the factors of variation include the position of the car, its color,
and the angle and brightness of the sun.
A major source of difficulty in many real-world artificial intelligence applications
is that many of the factors of variation influence every single piece of data we are
able to observe. The individual pixels in an image of a red car might be very close
to black at night. The shape of the car’s silhouette depends on the viewing angle.
Most applications require us to disentangle the factors of variation and discard the
ones that we do not care about.
Of course, it can be very difficult to extract such high-level, abstract features
from raw data. Many of these factors of variation, such as a speaker’s accent,
can be identified only using sophisticated, nearly human-level understanding of
the data. When it is nearly as difficult to obtain a representation as to solve the
original problem, representation learning does not, at first glance, seem to help us.
Deep learning solves this central problem in representation learning by intro-
ducing representations that are expressed in terms of other, simpler representations.
Deep learning enables the computer to build complex concepts out of simpler con-
cepts. Figure 1.2 shows how a deep learning system can represent the concept of
an image of a person by combining simpler concepts, such as corners and contours,
which are in turn defined in terms of edges.
The quintessential example of a deep learning model is the feedforward deep
network, or multilayer perceptron (MLP). A multilayer perceptron is just a
mathematical function mapping some set of input values to output values. The
function is formed by composing many simpler functions. We can think of each
application of a different mathematical function as providing a new representation
of the input.
The idea of learning the right representation for the data provides one per-
spective on deep learning. Another perspective on deep learning is that depth
enables the computer to learn a multistep computer program. Each layer of the
representation can be thought of as the state of the computer’s memory after
5
CHAPTER 1. INTRODUCTION
Output
CAR PERSON ANIMAL
(object identity)
Visible layer
(input pixels)
Figure 1.2: Illustration of a deep learning model. It is difficult for a computer to understand
the meaning of raw sensory input data, such as this image represented as a collection
of pixel values. The function mapping from a set of pixels to an object identity is very
complicated. Learning or evaluating this mapping seems insurmountable if tackled directly.
Deep learning resolves this difficulty by breaking the desired complicated mapping into a
series of nested simple mappings, each described by a different layer of the model. The
input is presented at the visible layer, so named because it contains the variables that
we are able to observe. Then a series of hidden layers extracts increasingly abstract
features from the image. These layers are called “hidden” because their values are not given
in the data; instead the model must determine which concepts are useful for explaining
the relationships in the observed data. The images here are visualizations of the kind
of feature represented by each hidden unit. Given the pixels, the first layer can easily
identify edges, by comparing the brightness of neighboring pixels. Given the first hidden
layer’s description of the edges, the second hidden layer can easily search for corners and
extended contours, which are recognizable as collections of edges. Given the second hidden
layer’s description of the image in terms of corners and contours, the third hidden layer
can detect entire parts of specific objects, by finding specific collections of contours and
corners. Finally, this description of the image in terms of the object parts it contains can
be used to recognize the objects present in the image. Images reproduced with permission
from Zeiler and Fergus (2014).
6
CHAPTER 1. INTRODUCTION
executing another set of instructions in parallel. Networks with greater depth can
execute more instructions in sequence. Sequential instructions offer great power
because later instructions can refer back to the results of earlier instructions. Ac-
cording to this view of deep learning, not all the information in a layer’s activations
necessarily encodes factors of variation that explain the input. The representation
also stores state information that helps to execute a program that can make sense
of the input. This state information could be analogous to a counter or pointer
in a traditional computer program. It has nothing to do with the content of the
input specifically, but it helps the model to organize its processing.
There are two main ways of measuring the depth of a model. The first view is
based on the number of sequential instructions that must be executed to evaluate
the architecture. We can think of this as the length of the longest path through
a flow chart that describes how to compute each of the model’s outputs given
its inputs. Just as two equivalent computer programs will have different lengths
depending on which language the program is written in, the same function may
be drawn as a flowchart with different depths depending on which functions we
allow to be used as individual steps in the flowchart. Figure 1.3 illustrates how this
choice of language can give two different measurements for the same architecture.
Element
Set σ Element
Set
+
+
× × × Logistic
Regression
Logistic
Regression
σ
w1 x1 w2 x2 w x
7
CHAPTER 1. INTRODUCTION
8
CHAPTER 1. INTRODUCTION
Representation learning
Machine learning
AI
Figure 1.4: A Venn diagram showing how deep learning is a kind of representation learning,
which is in turn a kind of machine learning, which is used for many but not all approaches
to AI. Each section of the Venn diagram includes an example of an AI technology.
target audience is software engineers who do not have a machine learning or statis-
tics background but want to rapidly acquire one and begin using deep learning in
their product or platform. Deep learning has already proved useful in many soft-
ware disciplines, including computer vision, speech and audio processing, natural
language processing, robotics, bioinformatics and chemistry, video games, search
engines, online advertising and finance.
This book has been organized into three parts to best accommodate a variety
of readers. Part I introduces basic mathematical tools and machine learning
concepts. Part II describes the most established deep learning algorithms, which
are essentially solved technologies. Part III describes more speculative ideas that
are widely believed to be important for future research in deep learning.
9
CHAPTER 1. INTRODUCTION
Output
Mapping from
Output Output
features
Additional
Mapping from Mapping from layers of more
Output
features features abstract
features
Hand- Hand-
Simple
designed designed Features
features
program features
Deep
Classic learning
Rule-based
machine
systems Representation
learning
learning
Figure 1.5: Flowcharts showing how the different parts of an AI system relate to each
other within different AI disciplines. Shaded boxes indicate components that are able to
learn from data.
Readers should feel free to skip parts that are not relevant given their interests
or background. Readers familiar with linear algebra, probability, and fundamental
machine learning concepts can skip part I, for example, while those who just want
to implement a working system need not read beyond part II. To help choose which
10
CHAPTER 1. INTRODUCTION
1. Introduction
3. Probability and
2. Linear Algebra
Information Theory
6. Deep Feedforward
Networks
11. Practical
12. Applications
Methodology
18. Partition
19. Inference
Function
Figure 1.6: The high-level organization of the book. An arrow from one chapter to another
indicates that the former chapter is prerequisite material for understanding the latter.
11
CHAPTER 1. INTRODUCTION
chapters to read, figure 1.6 provides a flowchart showing the high-level organization
of the book.
We do assume that all readers come from a computer science background. We
assume familiarity with programming, a basic understanding of computational
performance issues, complexity theory, introductory level calculus and some of the
terminology of graph theory.
• Deep learning has had a long and rich history, but has gone by many names,
reflecting different philosophical viewpoints, and has waxed and waned in
popularity.
• Deep learning has become more useful as the amount of available training
data has increased.
• Deep learning models have grown in size over time as computer infrastructure
(both hardware and software) for deep learning has improved.
We expect that many readers of this book have heard of deep learning as an exciting
new technology, and are surprised to see a mention of “history” in a book about an
emerging field. In fact, deep learning dates back to the 1940s. Deep learning only
appears to be new, because it was relatively unpopular for several years preceding
its current popularity, and because it has gone through many different names, only
recently being called “deep learning.” The field has been rebranded many times,
reflecting the influence of different researchers and different perspectives.
A comprehensive history of deep learning is beyond the scope of this textbook.
Some basic context, however, is useful for understanding deep learning. Broadly
speaking, there have been three waves of development: deep learning known as
cybernetics in the 1940s–1960s, deep learning known as connectionism in the
12
Other documents randomly have
different content
hänet makuulle. Itse hän istui vuoteen ääressä vielä pari tuntia.
Sairas nukkui sikeästi, liikahtamatta, hiljaa ja tasaisesti hengittäen.
Aljoša otti tyynyn ja kävi sohvalle makaamaan riisuutumatta. Ennen
nukkumistaan hän rukoili Mitjan ja Ivanin puolesta. Ivanin sairaus
kävi hänelle ymmärrettäväksi: »Ylpeän päätöksen tuskat, syvä
omatunto!» Jumala, johon hän ei uskonut, ja Hänen totuutensa olivat
valtaamassa sydämen, joka yhä vieläkään ei tahtonut alistua. »Niin»,
liikkui Aljošan mielessä hänen jo maatessaan pää tyynyllä, »niin, kun
kerran Smerdjakov on kuollut, niin Ivanin todistusta ei kukaan usko;
mutta hän menee ja todistaa!» Aljoša hymyili hiljaa: »Jumala
voittaa!» ajatteli hän. »Joko hän nousee ylös totuuden valossa, tai…
hän sortuu vihaan, kostaen itselleen ja kaikille siitä, että on palvellut
sitä, mihin ei usko», lisäsi Aljoša katkerasti ja rukoili taas Ivanin
puolesta.
Kahdestoista kirja
Tuomiovirhe
1.
Vaarallisia todistajia
— Saanko nyt tehdä teille kysymyksen, jollei teillä ole mitään sitä
vastaan, — kysyi Fetjukovitš yhtäkkiä ja aivan odottamatta, — mistä
aineista oli tehty se palsami eli niin sanoakseni se ryytiviina, jolla te
sinä iltana ennen maatamenoa, kuten tiedetään alustavasta
kuulustelusta, hieroitte kivistäviä lanteitanne toivoen siitä
parannusta?
— Oli pippuriakin.
— Ja niin edespäin. Ja kaikki tämä viinan seassa?
— Väkiviinassa.
— Join.
Grigori oli yhä vaiti. Yli salin kävi taas naurahdus. Puheenjohtaja
liikahti.
— Seisoin jaloillani.
— Se ei vielä todista, ettette nukkunut (taas kuului naurahduksia
salissa). Olisitteko esimerkiksi voinut vastata sillä hetkellä, jos joku
olisi kysynyt teiltä jotakin, — no, esimerkiksi sitä, mikä vuosi meillä
nyt on?
— Sitä en tiedä.
— Kaikki hänen puheensa ovat tosia, paitsi se, mitä hän sanoo
ovesta, — huudahti Mitja kovalla äänellä. — Siitä, että hän on
kammannut päästäni täit, minä kiitän, siitä, että hän on antanut
minulle anteeksi lyöntini, minä häntä kiitän; ukko on ollut rehellinen
koko elämänsä ajan ja niin uskollinen isälleni kuin seitsemänsataa
villakoiraa.
Our website is not just a platform for buying books, but a bridge
connecting readers to the timeless values of culture and wisdom. With
an elegant, user-friendly interface and an intelligent search system,
we are committed to providing a quick and convenient shopping
experience. Additionally, our special promotions and home delivery
services ensure that you save time and fully enjoy the joy of reading.
textbookfull.com