Page 175 - Robotics and AI class 10
P. 175
Artificial intelligence is an umbrella term that holds machine learning and deep learning. Deep learning follows a The drawback of this approach is that the learning for the machine is static, as once trained, the machine does not
specific learning approach which is a subset of machine learning comprising multiple machine learning algorithms. take into consideration any changes made in the original training dataset. If the machine is tested on a different
An important stage in the process of AI project cycle where we decide on the technique to be followed for dataset from the rules and the data fed in at the training stage, the machine will fail and will not learn from the
building a model from the prepared data. It is a mathematical approach in which an algorithm is designed as new conditions encountered.
per the requirement of the system which is ready to be installed to analyse the data technically. In the previous
stage of data exploration, we used the graphical representation of data to make it easy to understand the trends Learning Based Approach
and patterns. But when it comes to machines, it only understands the language of 1s and 0s so they only rely on This approach refers to the model where the relationship or patterns in the data are not defined by the developer.
mathematical representation of data. Random data is fed into the machine and the machine develops its own pattern or trends based on data outputs.
#Digital Literacy This approach is considered to take care of the challenges of rule-based systems.
Video Session For example, suppose you have a dataset of 1000 images of flowers. Now you do not have any clue as to what
trend is being followed in this dataset as you don’t know their names, colour or any other feature. Thus, you would
Scan the QR code or visit the following link to watch the video: put this into a learning approach-based AI machine and the machine would come up with various patterns it has
All Machine Learning Models Explained in 5 Minutes | Types of ML Models Basics observed in the features of these 1000 images.
https://www.youtube.com/watch?v=yN7ypxC7838&t=126s It might cluster the data on the basis of colour, size, shape, etc. It might also come up with some very unusual
clustering algorithm which you might not have even thought of!
The Learning Based Approach can further be divided into three sections:
Prediction Learning Based Approach
As the word suggests, prediction in AI refers to the outcome/output of an AI algorithm after it has been trained on
a historical dataset, used by the model on the new dataset while forecasting the likelihood of a particular event/
outcome. For example, the weather forecast is based on the current weather trend data, and the AI model uses Supervised Unsupervised Reinforcement
historical dataset over the new dataset available and predicts the weather expected in the near future. Learning Learning Learning
Approaches in AI Modelling Supervised Learning
An important stage in the process of AI project cycle where In a supervised learning model, a labelled dataset is given to the machine. A labelled dataset is the information
we decide on the technique to be followed for building a AI Models which is tagged with identifiers of data. For example, clothes in a store are marked under various categories of
model from the prepared data. It is a mathematical approach clothing like Shirts, Trousers, Coats, etc. They are further labelled as per gender and size. The Supervised Learning
in which an algorithm is designed as per the requirement of is further categorized as:
the system which is ready to be installed to analyse the data Rule Based Learning Based Regression
technically. In the previous stage of data exploration, we Approach Approach
used the graphical representation of data to make it easy to It is an example of rule-based AI model. This is a type of Rule Based AI model. In regression, the algorithm generates
understand the trends and patterns. But when it comes to machines, it only understands the language of 1s and a mapping function from the given data, as shown by the solid line in the given graph. The green dots shown in
0s so they only rely on mathematical representation of data. AI modelling techniques can be broadly classified into the graph are the data values and the solid line here represents the mapping done for them. With the help of this
the following two approaches: mapping function, we can predict the future data. For example, if we want to predict the temperature of a day in a
year, we can use past year’s temperature for that day as training data and can predict it for the coming year.
Rule Based Approach
This approach is based on a set of rules and facts defined by the developer and fed to the machine to perform its
task accordingly to generate the desired output. These models can operate with simple basic information and data.
To explain it further, let's take an example. If you have a dataset that consists of weather conditions, a basis which
we can predict if the lion would be visible on a specific Safari Day to the tourists. The parameters can be cloud Temperature
cover, temperature, wind speed, humidity. When these parameters are recorded and fed in the machine giving
the favourable combinations when the Lion would be visible and rest can be considered that the lion would not
be visible. Now, to test the model, the machine is given a scenario of the cloud cover, temperature, wind speed,
humidity. The model will compare the same with the fed in the dataset and if there is a match, would let know if
the lion would be visible or not. This is called a rule-based approach.
Year
Components of AI Project Framework 173

