CBSE-Intel AI-Thon

Frequently Asked Questions

INTRODUCTION TO ARTIFICIAL INTELLIGENCE

1) What is AI?

- AI is a form of intelligence; a type of technology and a field of study. AI theory and development of computer
systems (both machines and software) are able to perform tasks that normally require human intelligence.
Artificial Intelligence covers a broad range of domains and applications and is expected to impact every field in
the future. Overall, its core idea is building machines and algorithms which are capable of performing
computational tasks that would otherwise require human like brain functions.
- Resources to refer:
- https://www.weforum.org/platforms/shaping-the-future-of-technology-governance-artificial-
intelligence-and-machine-learning
- https://www.britannica.com/technology/artificial-intelligence
- http://www.europarl.europa.eu/RegData/etudes/STUD/2018/626074/IPOL_STU(2018)626074_EN.pdf
- https://niti.gov.in/writereaddata/files/document_publication/NationalStrategy-for-AI-Discussion-
Paper.pdf

2) What are the different domains of AI?

- Various domains of Artificial Intelligence are:

- Data Sciences - Working with Numeric and Alpha-Numeric datasets
- Computer Vision - Working with Image and Video datasets
- Natural Language Processing - Working with Textual and speech datasets

3) What are the various applications of AI?

- Depending upon datasets, various applications of Artificial Intelligence exists in today’s time. Some of them are:
- Data Science:
- Prediction of Air Quality
- Weather Forecasting
- Netflix
- Amazon Shopping, etc.
- Computer Vision
- Snapchat
- Image Editing Apps
- Face Lock
- Identity Recognition, etc.
- Natural Language Processing
- Auto-correct
- Text-to-Speech
- Speech Recognition
- Twitter, etc.
4) Define: AI,ML and DL

- Artificial Intelligence, or AI, refers to any technique that enables computers to mimic human intelligence.
The AI-enabled machines think algorithmically and execute what they have been asked for intelligently.

- Machine Learning, or ML, enables machines to improve at tasks with experience. The machine learns from
its mistakes and takes them into consideration in the next execution. It improvises itself using its own
experiences.

- Deep Learning, or DL, enables software to train itself to perform tasks with vast amounts of data. In deep
learning, the machine is trained with huge amounts of data which helps it into training itself around the
data. Such machines are intelligent enough to develop algorithms for themselves.

5) What are the different types of Approaches taken for building AI?

- Normally, two types of approaches come in picture for developing AI models:

- Rule-Based approach: Refers to the AI modelling where the rules are defined by the developer. The
machine follows the rules or instructions mentioned by the developer and performs its task accordingly.A
drawback/feature for this approach is that the learning is static. The machine once trained, does not take
into consideration any changes made in the original training dataset. That is, if you try testing my machine
on a dataset which is different from the rules and data you fed at the training stage, the machine would
fail on it and will not learn from its mistakes. Once trained, the model cannot improvise itself on the basis
of feedback.
- Learning-Based approach: Refers to the AI modelling where the machine learns by itself. Under the
Learning Based approach, the AI model gets trained on the data fed to it and then is able to design a model
which is adaptive to the change in data. That is, if the model is trained with X type of data and the machine
designs the algorithm around it, the model would modify according to the changes which occur in the
data so that all the exceptions are handled in this case.

6) Describe Machine Learning Model Families.

- Three types of model families exist under machine learning:

- Supervised Learning: Under Supervised Learning, the dataset on which the model gets trained is known
to the user and is labelled. By labelled dataset, we mean to say that each of the entry in the dataset has
been classified under a specific section of data. For example, in our results, we get grades corresponding
to our percentages. Here, grades can be taken as the label as it helps in analysing the data.
- Tool to experience Supervised Learning: https://teachablemachine.withgoogle.com/
- Unsupervised Learning: Under Unsupervised Learning, the dataset on which the model gets trained is not
known to the user and is unlabelled. By unlabelled dataset, we mean to say that the dataset is random
and the unsupervised model is used to make some sense out of it. For example, if a dataset of random
images is taken to train the unsupervised model, the model would cluster the image data on the basis of
various features or patterns observed in it. Hence, giving some clarity about it.
- Tool to experience Unsupervised Learning: experiments.withgoogle.com/ai/drum-machine/
- Reinforcement Learning: Under Reinforcement Learning, the model comes up with the best way of
completing a task. For example, if the model is asked to come up with the best way of reaching point B
from point A, the model would iterate all possible ways for fulfilling the task and would choose the best
way out of it and return it back to the user.
- Google Deep-Mind AI: https://www.youtube.com/watch?v=gn4nRCC9TwQ
7) What is a Neural Network?

- Neural networks are loosely modelled after how neurons in the human brain behave.
- Neural networks come under Deep Learning as they are used for efficient results for vast datasets.
- The key advantage of neural networks, is that they are able to extract data features automatically without needing
the input of the programmer.
- A neural network is essentially a system of organizing machine learning algorithms to perform certain tasks.
- It is a fast and efficient way to solve problems for which the dataset is very large, such as in images.

8) What is Python?

- Python is an interpreted, object-oriented, high-level programming language with dynamic semantics.

- Python's simple, easy to learn syntax emphasizes readability and therefore reduces the cost of program
maintenance.
- Python supports modules and packages, which encourages program modularity and code reuse.
- The Python interpreter and the extensive standard library are available in source or binary form without charge
for all major platforms, and can be freely distributed.

9) Why Python?

- Python is an open-source language which makes it easier for everyone to access and work upon.
- Since it is free to use, a lot of people work around Python hence there exists many packages and modules which
can directly be used while programming in Python. One does not need to write everything from scratch.
- The language is simple. There isn’t much syntax which needs to be learnt and it is also very user-friendly.

10) Mention some resources to learn Python.

- A lot of tutorials and courses are available online for free to learn python. Many of them offer basic working with
Python and a few also talk about advance learnings around it.
- Some of the resources are:
- https://docs.python.org/3/tutorial/
- https://www.tutorialspoint.com/python/index.htm
- https://www.datacamp.com/courses/intro-to-python-for-data-science
- https://www.w3schools.com/python/

11) What is a Jupyter Notebook?

- The Jupyter Notebook is an open source application that you can use to create and share documents that contain
live code, equations, visualizations, and text.

12) Why Jupyter Notebook?

- A lot of interfaces are available when it comes to working on Python. Jupyter Notebook is prefered because of its
user-friendliness.
- In a jupyter notebook, one can work around the combination of all - Text, Images, Live Code, etc.
- The understandability of concepts in Jupyter notebook becomes better.
 13) How to use Jupyter Notebook?

- To use Jupyter Notebook, you will need anaconda distribution of Python.

- Refer this link: https://docs.anaconda.com/anaconda/install/windows/ for step by step procedure to download
and install anaconda [Ignore step 2 in the process].
- Other resources to refer: https://jupyter-notebook.readthedocs.io/en/stable/notebook.html#notebook-user-
interface

DATA SCIENCE
1) What is AI for Data Science?

- Data science is the study of data. It involves developing methods of recording, storing, and analyzing data to
effectively extract useful information.
- The goal of data science is to gain insights and knowledge from any type of data — both structured and
unstructured.
- AI for data Science is the study of data, collection and analysis, etc. in order to predict important information out
of it.

2) Mention some applications of Data Sciences.

- Data Science is a very versatile field as its applications are quite diverse. Few applications are mentioned below:
- Targeted Advertising: Showing exact advertisements to user about what he wants.
- Google Maps: Navigating through the shortest route possible
- Weather Forecasting: Predicting the data for a short period of time by analysing weather patterns
- Recommender engines: Recommending what the user wants depending upon their choices
- Predictions: Predicting the result of a process on the basis of several previous outcomes

3) What are the basic statistical terms used for Data Analysis?

- Basic statistics are used for Data Analysis. Some of the functions used are:
- Mean: Mean is the sum of all the data points divided by the number of data points.
- Median: Median is the 50th percentile value and is useful if the distribution is skewed.
- Mode: Mode is the most frequent value and it can help us identify the most frequent occurence.
- Standard Deviation: Standard deviation is a measure of how spread out the numbers are and gives a
standard way of knowing what is normal. It is the square root of variance.
- Variance: Variance is the average of the squared differences from the mean.

4) Which graphical representations are widely used in Data Sciences?

- Various graphical representations can be used for data analysis. Some of them are mentioned below:
- Box plot
- Histogram
- Scatter plot
- Line graph
- Bar graph
5) What are packages? Which packages are commonly used in Data Science?

- A package is nothing but a space where you can find codes or functions or modules of similar type. There are
various packages readily available to use for free (perks of python being an open-source language) for various
purposes.
- Some of the packages commonly used for Data Sciences are:
- NumPy
- Matplotlib
- Pandas

6) What is NumPy?

- NumPy, which stands for Numerical Python, is the fundamental package for scientific computing in Python
consisting of high-performance multidimensional array objects and a collection of tools for working with those
arrays. Using NumPy, mathematical and logical operations on arrays can be performed.
- Read more about NumPy here:
- https://www.tutorialspoint.com/numpy/index.htm
- https://www.geeksforgeeks.org/numpy-in-python-set-1-introduction/
- https://www.datacamp.com/community/tutorials/python-numpy-tutorial

7) What is Matplotlib.PyPlot?

- Matplotlib is a plotting library for the Python programming language and its numerical mathematics extension
NumPy. It is a huge package which contains a lot of extensions to support other tools and packages in Python.
Here, for basic data science implementations, we use one of its attributes called PyPlot.
- Matplotlib.PyPlot is a plotting library used for 2D graphics in python programming language.
- We use Matplotlib.PyPlot to visualize data in graphical form to understand patterns, trends, abnormalities,
outliers,etc. Which also helps us understand which models to use for prediction.
- Read more about Matplotlib.PyPlot here:
- https://www.geeksforgeeks.org/python-introduction-matplotlib/
- https://matplotlib.org/3.1.1/tutorials/introductory/pyplot.html
- https://www.tutorialspoint.com/numpy/numpy_matplotlib.htm

8) What is Pandas?

- Pandas is an open source package providing high-performance, easy-to-use data structures and data analysis tools
for the python programming language.
- It is the most popular python library that is used for data analysis. It provides highly optimized performance with
back-end source code is purely written in Python.
- Read more about Pandas here:
- https://www.geeksforgeeks.org/python-data-analysis-using-pandas/
- https://datacamp.com/community/tutorials/pandas-tutorial-dataframe-python
- https://www.tutorialspoint.com/python_pandas/index.htm
COMPUTER VISION

1) What is Computer Vision in the field of AI ?

- Computer vision is a field of computer science that works on enabling computers to see, identify and process
images in the same way that human vision does, and then provide appropriate output.
- Read more about this here:
- https://en.wikipedia.org/wiki/Computer_vision
- https://www.techopedia.com/definition/32309/computer-vision

2) What are the some of the applications of computer vision ?

- Computer vision can be used for the following applications as follows:

- Barcode scanning
- Fingerprint sensor
- 3D scanning
- Facial recognition

3) Mention some of the image processing techniques used for Computer Vision.

- The different task in CV are :

- Classification
- Classification + Localisation
- Object Detection
- Instance Segmentation

4) What is a pixel?

- A pixel is the smallest unit of a digital image or graphic that can be displayed and represented on a digital display
device. A pixel is the basic logical unit in digital graphics. Pixels are combined to form a complete image, video,
text or any visible thing on a computer display.
- Read more about pixels here: https://www.techopedia.com/definition/24012/pixel

5) What is the range of pixel value in an image?

- A pixel value can vary from 0 to 255, where 0 represents no colour or black and 255 represents full colour or
white.

6) What is the difference between a grayscale and a colour image ?

- Grayscale image only has shades of black and white. Gray scale image is usually 8-bit image with each pixel having
256 combinations of shades of gray. It can be represented using just one plane/channel of pixels.
- Whereas color image usually is a 24 bit image with 8-bits of Red, 8-bits of Green, 8-bits for blue information. It
can be represented using three planes/ channels one each of Red, Green and Blue.
- For more reading, refer to the resources below:
- http://aishack.in/tutorials/color-spaces-1/
- https://www.allaboutcircuits.com/technical-articles/understanding-color-models-used-in-digital-image-
processing/
 7) What is OpenCV?

- OpenCV (Open Source Computer Vision Library) is an open source computer vision and machine learning
software library which provides the user with various image-processing tools which can be easily used for any
Computer Vision application.
- To read more, refer to this link: https://opencv.org/about/

8) What are the basic functions in OpenCV available for Image Processing?

- Some of the basic functions in the OpenCV library are as follows:

- Cv2.imread() – To open an image
- Cv2.imshow() – To display an image
- Cv2.destroyAllWindows() – To simply close all windows we have created
- Cv2.imwrite() – To save an image
- Cv2.resize() – To resize an image
- To read more, refer to these links:
- https://opencv-python-
tutroals.readthedocs.io/en/latest/py_tutorials/py_gui/py_image_display/py_image_display.html
- https://opencv-python-
tutroals.readthedocs.io/en/latest/py_tutorials/py_core/py_basic_ops/py_basic_ops.html
- https://www.programcreek.com/python/example/89426/cv2.cvtColor

NATURAL LANGUAGE PROCESSING

1) What is Natural Language Processing in AI?

- Natural Language Processing (or NLP) is a domain of Artificial Intelligence which works around speech and textual
data. The AI models working in the domain of NLP focus majorly on text interpretation, speech recognition,
meaning extraction, etc.

2) Mention some of the applications of Natural Language Processing.

- Some applications of Natural Language Processing commonly used today are:

- Machine Translation, making sure that the essence of the statement is not lost.
- Automatic Summarisation, on the basis of the important words identified in the content.
- Sentiment Analysis, identifying opinions and sentiments to help in understanding people’s state of mind.
- Text Classification, to filter out unnecessary data and prioritise the importance ones.
- Image/Video Captioning, saving time and hassle.
- Chatbots, carrying out human-like conversations.
- Assistants, personalising the bot with data and natural language.
- Search Results, analysing the keywords and prioritising information sources according to their relevance.

3) What is a chatbot? What is their importance?

- A chatbot is an artificial intelligence (AI) software that can simulate a conversation (or chat) with a user in natural
language through messaging applications, websites, mobile apps or through the telephone.
- A chatbot is often described as one of the most advanced and promising expressions of interaction between
humans and machines. However, from a technological point of view, a chatbot only represents the natural
evolution of a Question Answering system leveraging Natural Language Processing (NLP). Formulating responses
to questions in natural language is one of the most typical Examples of Natural Language Processing applied in
various enterprises’ end-user applications.
4) Mention some examples of chatbots.

- Here are some examples of Chatbots:

- Mitsuku Bot - https://www.pandorabots.com/mitsuku/
- CleverBot - https://www.cleverbot.com/
- Jabberwacky - http://www.jabberwacky.com/
- Haptik - https://haptik.ai/contact-us
- Rose - http://ec2-54-215-197-164.us-west-1.compute.amazonaws.com/speech.php
- Ochatbot - https://www.ometrics.com/blog/list-of-fun-chatbots/

5) What are the tasks which could be performed under Natural Language Processing?

- Since Natural Language Processing majorly deals with text processing, following are some operations that are
performed under NLP:
- Sentence Segmentation: Dividing the whole text into sentences.
- Tokenization: Separating sentences into words, numbers and special characters.
- Removing Stop words: Cleaning textual data by removing words with minimal importance.
- Case Conversion: Converting the whole data in same case (preferably lower case)
- Stemming: Reducing words to their root form (example: stepping, stepped, stepper becomes step)
irrespective of root word being a meaningful word.
- Lemmatization: Reducing words to their root form (same as stemming) making sure that the root word is
a meaningful one.
- Bag of words: Creating vocabulary for the textual data and calculating the occurence of words in the
dataset.
- TFIDF: Term Frequency - Inverse Document Frequency is the tool through which we can understand the
value of a word in the whole dataset.
- Read more about these tools here:
- https://www.geeksforgeeks.org/text-preprocessing-in-python-set-1/
- https://medium.com/@datamonsters/text-preprocessing-in-python-steps-tools-and-examples-
bf025f872908

6) What are the resources to refer for text processing tools?

- Sentence Segmentation: https://tinyurl.com/y36hd92n

- Tokenization: https://text-processing.com/demo/tokenize/
- Stop word removal: https://demos.datasciencedojo.com/demo/stopwords/
- Case Converter : https://caseconverter.com/
- Stemming: http://textanalysisonline.com/nltk-porter-stemmer
- Lemmatization: http://textanalysisonline.com/spacy-word-lemmatize
- Bag of Words:
- https://medium.com/greyatom/an-introduction-to-bag-of-words-in-nlp-ac967d43b428
- https://www.geeksforgeeks.org/bag-of-words-bow-model-in-nlp/
- https://machinelearningmastery.com/gentle-introduction-bag-words-model/
- TFIDF:
- https://medium.com/greyatom/an-introduction-to-bag-of-words-in-nlp-ac967d43b428
- https://towardsdatascience.com/natural-language-processing-feature-engineering-using-tf-idf-
e8b9d00e7e76
7) What is NLTK?

- Natural Language Tool-Kit or NLTK is a package readily available for text-processing in Python.
- The package contains functions and modules which can be used for Natural Language Processing.
- Read further about the package here:
- https://www.nltk.org/
- https://pythonspot.com/category/nltk/
- https://www.datacamp.com/community/tutorials/text-analytics-beginners-nltk