8. IN 1943
Mathematical
Neural networking
modeling:
Walter Pitts and
Warren McCulloh
Published first
mathematical modeling
of a Neural Network.
IN 1950 The Tuning Test:
Alan Turing Published
an article answering
the questions CAN
MACHINES THINK?
IN 1952
Arthur Samuel's
Cheekers program:
A program for IBM
computer.
IN 1956
Research project in
Dartmouth College:
John McCarthy
invited
mathematicians for
Six to eight weeks
event about AI.
11. Machine learning is a form of Artificial Intelligence that teaches
computer to think in a similar way to how humans do: learning and
improving upon past experiences. It works by exploring data,
identifying patterns, and invovles minimal human intervention
Gathering
data
Preparing
data
Train Mode
Test Data
Improve
16. In this type, the model is trained on a labeled dataset,
meaning that each example in the training data has a
known label. The model can then make predictions on
new, unlabeled data
INPUT FUNTION
OUTPU
T
19. Classification problems use an algorithm to accurately
assign test data into specific categories, such as separating
apples from oranges or to classify spam in a separate folder
from your inbox by supervised algorithm
Linear classifiers, support vector machines, decision trees
and random forest are all common types of classification
algorithms
20. Regression uses an algorithm to understand the relationship
between dependent and independent variables based on different
data points, such as sales revenue projections for a given business
Some popular regression algorithms are
22. Unsupervised learning uses machine learning algorithms to analyze
and cluster unlabeled data sets. The model can then find hidden
patternsorgroupsinthedatawithouthumanintervention.
UNLABELL
ED DATA MACHINE RESUL
TS
24. Clustering is a data mining technique for grouping unlabeled data
based on their similarities or differences.
Independent Input
Variables
Classification
Model
Vegetables Groceries
Categorical Output
Variable
25. Association is another type of unsupervised learning method that uses different
rules to find relationships between variables in a given dataset.
27. In this type, the model is trained by interacting with an
environment where it receives rewards or punishments for its
actions and then be used to make decisions in new situations to
maximize its rewards.
39. Easily identifies trends and pattern.
No human intervention needed. (Automation)
Continuous improvement.
Handling multi-dimensional and multi-variety data.
Wide Applications.
40. Data Acquisition
TIME AND RESOURCES
High error-susceptibility
Interpretation of Results
Algorithm selection