Information Technology Reference
In-Depth Information
4.2.3.1 Inspiring Set
The inspiring set contains soup, stew, and chili recipes gathered from popular online
recipe websites.
6
From these recipes we manually create both a list of measurements
and ingredients in order to parse recipes into a consistent format. This parsing enables
(1) grouping identical ingredients under a common name, (2) grouping similar ingre-
dients at several levels, and (3) gathering statistics about ingredients and ingredient
groups across the inspiring set. Recipes in the inspiring set are normalized to 100
ounces.
The database of ingredients is explicitly partitioned into a hierarchy in which
similar ingredients are grouped at a
sub
-level and these ingredient groups are further
grouped at a
super
-level. For example, as shown in Fig.
4.6
, the super-group
Fruits
and Vegetables
is composed of the sub-groups
Beans
,
Fruits
,
Leafy Vegetables
, and
others. The sub-group of
Beans
includes many different types of beans including
Butter Beans
,
Red Kidney Beans
,
Garbanzo Beans
, and others.
Statistics (minimum, maximum, mean, standard deviation, and frequency) are
kept for each ingredient. These statistics are also aggregated at the sub- and super-
group levels, enabling comparison and evaluation of recipes at different levels of
abstraction. In addition, gathering statistics at the group level provides a mechanism
for smoothing amounts for rare ingredients. Each statistic
for such ingredients is
linearly interpolated with the corresponding statistic of the sub-group, according to
the following:
ˉ
ʱ
ʱ
+
ʲ
x
ʲ
ʱ
+
ʲ
+
ʾ
if
ʱ<ʸ
ˉ
=
(4.6)
x
if
ʱ
≥
ʸ
where
x
is the raw statistic of the ingredient,
ʾ
is the statistic of the sub-group,
ʱ
ʲ
is the number of times the ingredient occurs in the inspiring set,
is the number
of times any of the sub-group ingredients occur in the inspiring set, and the rarity
threshold
is set to 100.
The inspiring set is used differently for generation than it is for evaluation. During
artifact generation (Sect.
4.2.3.2
) the inspiring set determines the initial population
used for the genetic algorithm. During artifact evaluation (Sect.
4.2.3.3
) the inspir-
ing set determines which recipes and ratings are used as training examples. Since
the inspiring set is used in multiple ways, employing a different inspiring set for
generating artifacts than the one used to evaluate artifacts can have useful effects.
ʸ
4.2.3.2 Generation
PIERRE generates new recipes using a genetic algorithm acting on a population of
recipes, each composed of a list of ingredients. The population is initialized by choos-
ing recipes uniformly at random from the inspiring set, and the fitness of each recipe
6
Search WWH ::
Custom Search