Professional Documents
Culture Documents
A Review On Machine Learning Algorithms, Tasks and Applications
A Review On Machine Learning Algorithms, Tasks and Applications
net/publication/320609700
CITATIONS READS
43 14,957
2 authors, including:
Neeraj Kumar
Chitkara University
47 PUBLICATIONS 166 CITATIONS
SEE PROFILE
Some of the authors of this publication are also working on these related projects:
All content following this page was uploaded by Neeraj Kumar on 25 October 2017.
1548
All Rights Reserved © 2017 IJARCET
International Journal of Advanced Research in Computer Engineering & Technology (IJARCET)
Volume 6, Issue 10, October 2017, ISSN: 2278 – 1323
1549
All Rights Reserved © 2017 IJARCET
International Journal of Advanced Research in Computer Engineering & Technology (IJARCET)
Volume 6, Issue 10, October 2017, ISSN: 2278 – 1323
(iv) Decide the structure of the learned punishments as it navigates its problem
function and corresponding learning space.
algorithm.
III. MACHINE LEARNING
(v) Complete the design. Run the learning ALGORITHMS
algorithm on the gathered training set. Some
There are number of machine learning
supervised learning algorithms need the user
algorithms such as Linear Regression,
to find out certain control parameters.
Logistic Regression, Decision Tree, SVM
(vi) Assess the accuracy of the learned [2], and KNN. Linear Regression is used to
function. After parameter adjustment and estimate real values (cost of houses, number
learning, the performance of the resulting of calls, total sales etc.) based on continuous
function should be measured on a test set variable(s). Here, we establish relationship
that is separate from the training set. between independent and dependent
variables by fitting a best line. Logistic
Unsupervised learning: It is the machine
Regression is used to estimate discrete
learning task of inferring a function to depict
values based on given set of independent
concealed structure from "unlabeled" data.
variable(s). In simple words, it predicts the
Since the examples specified to the learner
probability of occurrence of an event by
are unlabeled, there is no assessment of the
fitting data to a logit function. Decision Tree
accuracy of the structure that is output by
is a type of supervised learning algorithm
the relevant algorithm—which is one way of
that is mostly used for classification
distinguishing unsupervised learning from
problems.SVM is a classification method. In
supervised learning and reinforcement
this algorithm, we plot each data item as a
learning. A central case of unsupervised
point in n-dimensional space (where n is
learning is the problem of density estimation
number of features you have) with the value
in statistics [1].
of each feature being the value of a
Reinforcement learning: A computer particular coordinate. K nearest neighbors is
program interacts with a vibrant a simple algorithm which stores the entire
environment in which it must perform a available cases and classifies new cases by a
certain goal. The program is provided majority vote of its k neighbors.
feedback in terms of rewards and
1550
All Rights Reserved © 2017 IJARCET
International Journal of Advanced Research in Computer Engineering & Technology (IJARCET)
Volume 6, Issue 10, October 2017, ISSN: 2278 – 1323
V.CONCLUSION
VI. REFERENCES
1551
All Rights Reserved © 2017 IJARCET
International Journal of Advanced Research in Computer Engineering & Technology (IJARCET)
Volume 6, Issue 10, October 2017, ISSN: 2278 – 1323
1552
All Rights Reserved © 2017 IJARCET
View publication stats