This document provides an introduction to machine learning and related concepts. It discusses artificial intelligence and how machine learning is a type of AI that allows systems to learn from experience without being explicitly programmed. The document then covers various machine learning topics like neural networks, deep learning, data science, the prerequisites of machine learning, different types of machine learning including supervised learning, unsupervised learning and reinforcement learning. It also discusses popular usages of machine learning and why Python is a good programming language for machine learning. Finally, it introduces the Anaconda distribution and Jupyter Notebook as useful tools for machine learning.

1. Welcome

2. Machine Learning
By: Abu Saleh Muhammad Shaon
Engineer at VroomVroomVroom Ptv Ltd
Machine
Learning

3. To be discussed
❏ Introduction of machine learning & related terms
❏ Types of machine learning and explanation
❏ Why Python is best for machine learning?
❏ Anaconda Distribution
❏ Jupyter Notebook

5. Artificial Intelligence (AI)
❏ Artificial intelligence (AI) is an area of computer science that
emphasizes the creation of intelligent machines that work and
react like humans.
❏ Artificial Intelligence (AI) combines science and engineering in
order to build machines capable of intelligent behaviour.

6. ❏ Machine learning is an application of artificial intelligence (AI)
that provides systems the ability to automatically learn and
improve from experience without being explicitly programmed.
❏ Machine learning focuses on the development of computer
programs that can access data and use it learn for themselves.
Machine Learning (ml)

7. ❏ Neural networks is a beautiful biologically-inspired programming
paradigm which enables a computer to learn from observational
data.
❏ Neural networks are a set of algorithms, modeled loosely after
the human brain, that are designed to recognize patterns.
Neural Networks

8. ❏ Deep learning, a powerful set of techniques for learning in neural
networks.
❏ Deep Learning is a machine learning method. It allows us to train
an AI to predict outputs, given a set of inputs. Both supervised
and unsupervised learning can be used to train the AI.
Deep Learning

9. Data science is an interdisciplinary field that uses scientific methods,
processes, algorithms and systems to extract knowledge and insights
from data in various forms, both structured and unstructured,
similar to data mining.
Data Science

10. ❏ A person employed to analyse and interpret complex digital data,
such as the usage statistics of a website, especially in order to
assist a business in its decision-making.
❏ "Silicon Valley technology companies are hiring data scientists to
help them glean insights from the terabytes of data that they
collect everyday"
Data Scientist

12. ❏ A pattern should exist.
❏ The mathematical model unknown.
❏ There should be lots of DATA
Prerequisites of Machine Learning

13. ❏ Supervised learning (classification • regression)
❏ Unsupervised learning
❏ Semi-supervised learning
❏ Reinforcement learning
❏ Structured prediction
Types of Machine Learning

14. Supervised learning is a type of system in which both input and
desired output data are provided. Input and output data are labelled
for classification to provide a learning basis for future data
processing.
Supervised Learning

15. Unsupervised learning is the training of an algorithm using
information that is neither classified nor labeled and allowing the
algorithms learn from a dataset without the outcome variable.
UnSupervised Learning

16. Semi-supervised learning falls in between supervised and
unsupervised learning and works well with partially labeled data.
In semi-supervised learning, an algorithm learns from a dataset that
includes both labeled and unlabeled data.
Semi-Supervised Learning

17. ❏ learning focuses on decision processes and reward systems. It’s
able to learn a series of actions.
❏ Let’s imagine that a new born baby comes across a lit candle.
Now, the baby does not know what happens if it touches the
flame. Eventually, out of curiosity, the baby tries to touch the
flame and gets hurt. After this incident, the baby learns that
repeating the same thing again might get him hurt. So, the next
time it sees a burning candle, it will be more cautious.
Reinforcement Learning

18. Reinforcement Learning

19. Reinforcement Learning

20. ❏ Email filtering. Inboxes are equipped with machine learning to
help sift through spam.
❏ Online recommendations. Retail sites use machine learning to
offer you personalized recommendations based on your previous
purchases or activity.
❏ Stock market prediction
Top Usages of Machine Learning

21. ❏ Voice recognition. Siri, Alexa, and other voice recognition
systems use machine learning as part of their technology toolkit
to imitate human interactions and continue to “understand” users
better.
❏ Face recognition. Sites like Facebook use machine learning
algorithms to recognize familiar faces and identify who is in a
photo.
Top Usages of Machine Learning

22. ❏ Python is open source programming language and is freely
available
❏ Quick to install and write your first programm
❏ Simple & elegant syntax
❏ Python is easy to learn
Why Python is best for ML ?

23. ❏ Out of box libraries for data analysis like pandas, scikit-learn,
Numpy, matplotlib etc
❏ Popularity of Python
❏ Loved by data scientists, default programming language for data
scientists
Why Python ?

24. Most powerful Algorithms

25. The open-source Anaconda Distribution is the easiest way to perform
Python/R data science and machine learning on Linux, Windows, and
Mac OS X. With over 11 million users worldwide, it is the industry
standard for developing, testing, and training on a single machine,
enabling individual data scientists to.
Anaconda

26. ❏ Quickly download 1,500+ Python/R data science packages
❏ Manage libraries, dependencies, and environments with Conda
❏ Develop and train machine learning and deep learning models
with scikit-learn, TensorFlow, and Theano
Anaconda

27. ❏ Analyze data with scalability and performance with Dask, NumPy,
pandas, and Numba
❏ Visualize results with Matplotlib, Bokeh, Datashader, and
Holoviews
Anaconda

28. Anaconda Navigator is a desktop graphical user interface (GUI)
included in Anaconda distribution that allows users to launch
applications and manage conda packages, environments and
channels without using command-line commands
Anaconda Navigator

29. ❏ JupyterLab, Jupyter Notebook
❏ Qt Console, Spyder
❏ Glueviz, Orange
❏ Rstudio, Visual Studio Code
Anaconda Navigator - Tools

30. ❏ The Jupyter Notebook is an incredibly powerful tool for
interactively developing and presenting data science projects.
❏ A notebook integrates code and its output into a single
document that combines visualisations, narrative text,
mathematical equations, and other rich media.
❏ It’s increasingly popular choice at the heart of contemporary
data science, analysis etc
Jupyter Notebook

31. Demo
Lets see how we can work with Anaconda & Jupyter
Notebook

32. ❏ https://towardsdatascience.com/how-to-setup-a-python-environment-for-machine-lea
rning-354d6c29a264
❏ https://medium.com/cracking-the-data-science-interview/the-10-statistical-techniques
-data-scientists-need-to-master-1ef6dbd531f7
❏ https://www.geeksforgeeks.org/supervised-unsupervised-learning/
❏ https://mcalglobal.com/2018/02/22/machine-learning-hello-world-using-python/
❏ https://www.dataquest.io/blog/jupyter-notebook-tutorial/
❏ https://mcalglobal.com/2018/02/22/machine-learning-hello-world-using-python/
❏ https://blog.usejournal.com/stock-market-prediction-by-recurrent-neural-network-on-
lstm-model-56de700bff68

33. Thank you all