Kinds of Task

Reasoning
Machine learning algorithms

Kinds of Task
Classification
In this type of task, the computer program is asked to specify which of k

categories some input belongs to.
The learning algorithm is usually asked to produce a function f : R n→

{1,...,k}.
When y = f(x), the model assigns an input described by vector x to a

category
identified by numeric code y.
classification task is object recognition, where the input is an image (usually

described as a set of pixel brightness values), and the output is a numeric
code identifying the object in the image.
Classification with missing inputs
When some of the inputs may

be missing, rather than providing a single classification function, the
learning
algorithm must learn from a set of functions.
Each function corresponds to classifying x with a different subset of its

inputs missing.
This kind of situation arises frequently in medical diagnosis, because many

kinds of medical tests are expensive or invasive.
learn distribution over all variables, solve

by marginalizing over missing variables
Regression
In this type of task, the computer program is asked to predict a numerical

value given some input.
To solve this task, the learning algorithm

is asked to output a function f : R n → R
regression task is the prediction of the expected claim amount that an

insured person will make (used to set insurance premiums), or the
prediction of future prices of securities.
Transcription
In this type of task, the machine learning system is asked to observe a
relatively unstructured representation of some kind of data and transcribe it
into discrete, textual form.
In optical character recognition, the computer program is shown a

photograph containing an image of text and is asked to return this text in
the form of a sequence of characters (e.g., in ASCII or Unicode format).
In speech recognition, where the computer program is provided an audio

waveform and emits a sequence of characters or word
ID codes describing the words that were spoken in the audio recording.
Google Cloud speech, Google street view
Machine translation
In a machine translation task, the input already consists of a sequence of

symbols in some language, and the computer program
must convert this into a sequence of symbols in another language.
This is commonly applied to natural languages, such as translating from

English to French.
Structured output
Structured output tasks involve any task where the output is a vector with
important relationships between the different elements.
1. parsing—mapping a natural language sentence into a tree that describes

its grammatical structure and tagging nodes of the trees as being verbs,
nouns, or adverbs, and so on.
2. Pixel-wise segmentation of images, where the computer program assigns

every pixel in an image to a specific category.
3. Image captioning, the computer program observes an image and outputs

a natural language sentence describing the image
Anomaly detection
In this type of task, the computer program sifts through a set of events or
objects, and flags some of them as being unusual or atypical.
Anomaly detection task is credit card fraud

detection. By modeling your purchasing habits, a credit card company can
detect misuse of your cards.
The credit card company can prevent fraud by placing a hold on an account
as soon as that card has been used for an uncharacteristic purchase.
Synthesis and sampling
In this type of task, the machine learning algorithm is asked to generate

new examples that are similar to those in the training data.
Machine learning can be useful
for media applications where it can be expensive or boring for an artist to
generate large volumes of content by hand.
Video games can automatically generate textures for large objects or

landscapes, rather than requiring an artist to manually label each pixel.
In a speech synthesis task, we provide a written sentence and ask the

program to emit an audio waveform containing a spoken version of that
sentence.
Imputation of missing values
In this type of task, the machine learning

algorithm is given a new example x ∈ Rn
, but with some entries xi of x missing. The algorithm must provide a
prediction of the values of the missing entries.
Denoising
In this type of task, the machine learning algorithm is given in input a

corrupted example ˜x∈ R n obtained by an unknown corruption process
from a clean example x∈ Rn.
Density estimation or probability mass function estimation
In the density estimation problem, the machine learning algorithm is asked

to learn a function p model : Rn→ R, where p
model(x) can be interpreted as a probability density function (if x is
continuous) or a probability mass function.

Kinds of Task

Uploaded by

Copyright:

Available Formats

Kinds of Task

Uploaded by

Document Information

Original Description:

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Kinds of Task

Uploaded by

Copyright:

Available Formats

Reasoning

Machine learning algorithms

In this type of task, the computer program is asked to specify which of k

The learning algorithm is usually asked to produce a function f : R n→

When y = f(x), the model assigns an input described by vector x to a

classification task is object recognition, where the input is an image (usually

Classification with missing inputs

When some of the inputs may

Each function corresponds to classifying x with a different subset of its

This kind of situation arises frequently in medical diagnosis, because many

learn distribution over all variables, solve

In this type of task, the computer program is asked to predict a numerical

To solve this task, the learning algorithm

regression task is the prediction of the expected claim amount that an

In optical character recognition, the computer program is shown a

In speech recognition, where the computer program is provided an audio

Google Cloud speech, Google street view

In a machine translation task, the input already consists of a sequence of

This is commonly applied to natural languages, such as translating from

1. parsing—mapping a natural language sentence into a tree that describes

2. Pixel-wise segmentation of images, where the computer program assigns

3. Image captioning, the computer program observes an image and outputs

Anomaly detection task is credit card fraud

Synthesis and sampling

In this type of task, the machine learning algorithm is asked to generate

Video games can automatically generate textures for large objects or

In a speech synthesis task, we provide a written sentence and ask the

Imputation of missing values

In this type of task, the machine learning

In this type of task, the machine learning algorithm is given in input a

Density estimation or probability mass function estimation

In the density estimation problem, the machine learning algorithm is asked

You might also like