Machine Learning and its Applications

A presentation related to Introduction to Machine Learning

1. MACHINE LEARNING AND ITS APPLICATIONS SUBMITTED TO: SUBMITTED BY: Er . SEEMA RANI Bhuvan Chopra 2316011 © 2019 BHU_FILES under AMBALA COLLEGE OF ENGINEERING AND APPLIED RESEARCH | All Rights Reserved

2. TABLE OF CONTENTS: MACHINE LEARNING(INTRODUCTION) DIFFERENCE BASIC PREREQUISITES TYPES APPLICATIONS EXAMPLE © 2019 BHU_FILES under AMBALA COLLEGE OF ENGINEERING AND APPLIED RESEARCH | All Rights Reserved

3. WHAT IS MACHINE LEARNING? Machine Learning Herbert Alexander Simon : “Learning is any process by which a system improves performance from experience.” Turing Award 1975 and Nobel Prize in Economics 1978  Herbert Simon “Machine Learning is concerned with computer programs that automatically improve their performance through experience. “ © 2019 BHU_FILES | All Rights Reserved

4. MORE TO MACHINE LEARNING  In basic terms, ML is the process of training a piece of software, called a model. to make useful predictions using a data set. This predictive model can then serve up predictions about previously unseen data. We use these predictions to take action in a product; for example, the system predicts that a user will like a certain video, so the system recommends that video to the user. DATASET EXAMPLES: https://mailchi.mp/start/q86rfojms6-358025?e=3c53d9959f

5. A BASIC HISTORY..

6. Difference between Artificial Intelligence, Machine learning, and deep learning Artificial Intelligence “The ability of machines to work and think, like the human brain, is called Artificial Intelligence.” AI thinks, work, and reacts similarly to humans as it is designed in that way. However, Establishing the AI ultimately in our lives is not possible until now because there are many features of the human brain which are unable to describe. Some of the best examples of AI are face recognition on Facebook and images classification service of Interest. There are several cases of Artificial Intelligence, which we come through every day.

7. PICTORIAL VIEW 

8. Machine learning Machine learning is a part of Artificial Intelligence. Most of the people consider it as Artificial Intelligence, but it's not true. The machines can learn. The robots learn themselves from the data provided to them. It makes more like to be a technique which makes us realize the presence of Artificial Intelligence. This technique uses algorithms to get data, learn, and then analyze the data. The results came in the form of predictions. You may have noticed when getting recommendation on shopping sites, Google, or Facebook. You get suggestions according to your interests. It is done with machine learning algorithms which are developed in the way to analyzing the recent searches, history, and other information. This technique also influences the marketing and banking sectors. “Machine learning is the tendency of machines to learn from data analysis and achieve Artificial Intelligence.”

9. New machine learning algorithms were limited to basic AI, but now it has become an essential part of this system. Many complex algorithms are prepared to give better experience. It has turned the way of watching Shows and Movies. The entertainment industry is using this algorithm for providing suitable suggestions for its viewers on web channels like Netflix and Amazon Prime.  Machine learning is the concept of analyzing data and offers excellent recommendations based on learning from those points if you have questioned how the technique is implemented then read the next section that is Deep learning.

10. COMPANIES USING MACHINE LEARNING 

11. DEEP LEARNING Deep learning  is a subset of machine learning that's based on artificial neural networks. The  learning process  is  deep   because the structure of artificial neural networks consists of multiple input, output, and hidden layers. Each layer contains units that transform the input data into information that the next layer can use for a certain predictive task. Thanks to this structure, a machine can learn through its own data processing.

12. Prerequisites and Prework Mastery of intro-level algebra.  You should be comfortable with variables and coefficients, linear equations, graphs of functions, and histograms. (Familiarity with more advanced math concepts such as logarithms and derivatives is helpful, but not required.) Proficiency in programming basics, and some experience coding in Python, writing Python code that contains basic programming constructs, such as function definitions/invocations, lists and dicts , loops, and conditional expressions. Pandas: pandas  is a column-oriented data analysis API. It's a great tool for handling and analyzing input data, and many ML frameworks support  pandas  data structures as inputs. Although a comprehensive introduction to the  pandas  API would span many pages, the core concepts are fairly straightforward. For a more complete reference, the  pandas  docs site  contains extensive documentation and many tutorials. © 2019 BHU_FILES under AMBALA COLLEGE OF ENGINEERING AND APPLIED RESEARCH | All Rights Reserved

13. Math Algebra Variables ,  coefficients , and  functions Linear equations  such as y=b+w1x1+w2x2 Logarithms , and logarithmic equations such as y=ln(1+ez) Sigmoid function Linear algebra Tensor and tensor rank Matrix multiplication Trigonometry Tanh  (discussed as an  activation function ; no prior knowledge needed) Statistics Mean, median, outliers , and  standard deviation Ability to read a  histogram

14. Python Programming Basic Python The following Python basics are covered in  The Python Tutorial : Defining and calling functions , using positional and  keyword  parameters Dictionaries ,  lists ,  sets  (creating, accessing, and iterating) for loops ,  for  loops with multiple iterator variables (e.g.,  for a, b in [(1,2), (3,4)] ) if/else conditional blocks  and  conditional expressions String formatting  (e.g.,  '%.2f' % 3.14 ) Variables, assignment,  basic data types  ( int ,  float ,  bool ,  str ) The  pass statement

15. Third-Party Python Libraries Matplotlib  (for data visualization) Seaborn  (for heatmaps) pandas  (for data manipulation) NumPy  (for low-level math operations) scikit -learn  (for evaluation metrics) Keras PyTorch

16. Traditional Programming and Machine Learning The above figure shows traditional programming and next is of machine learning:

17. TYPES OF MACHINE LEARNING © 2019 BHU_FILES under AMBALA COLLEGE OF ENGINEERING AND APPLIED RESEARCH | All Rights Reserved

18. SUPERVISED LEARNING: machine learning takes data as input. lets call this data  Training data. For example, suppose you are an amateur botanist determined to differentiate between two species of the Lilliputian plant genus (a completely made-up plant). The two species look pretty similar. Fortunately, a botanist has put together a data set of Lilliputian plants she found in the wild along with their species name. Here's a snippet of that data set:

19. GOAL Leaf width and leaf length are the  features  (which is why the graph below labels both of these dimensions as X), while the species is the label. A real life botanical data set would probably contain far more features (including descriptions of flowers, blooming times, arrangement of leaves) but still have only one label. Features are measurements or descriptions; the label is essentially the "answer." For example, the goal of the data set is to help other botanists answer the question, "Which species is this plant?“ In  supervised machine learning , you feed the features and their corresponding labels into an algorithm in a process called  training . During training, the algorithm gradually determines the relationship between features and their corresponding labels. Often times in machine learning, the model is very complex. However, suppose that this model can be represented as a line that separates big-leaf from small-leaf: © 2019 BHU_FILES under AMBALA COLLEGE OF ENGINEERING AND APPLIED RESEARCH | All Rights Reserved

20. GRAPH

21. FINAL GRAPH:

22. NUTSHELL To tie it all together, supervised machine learning finds patterns between data and labels that can be expressed mathematically as functions. Given an input feature, you are telling the system what the expected output label is, thus you are supervising the training. The ML system will learn patterns on this labeled data. In the future, the ML system will use these patterns to make predictions on data that it did not see during training. An exciting real-world example of supervised learning is a  study from Stanford University  that used a model to detect skin cancer in images.

23. Unsupervised Learning In unsupervised learning, the goal is to identify meaningful patterns in the data. To accomplish this, the machine must learn from an unlabeled data set. In other words, the model has no hints how to categorize each piece of data and must infer its own rules for doing so. In the following graph, all the examples are the same shape because we don't have labels to differentiate between examples of one type or another here: Fitting a line to unlabeled points isn't helpful. We still end up with examples of the same shape on both sides of the line. Clearly we will have to try a different approach. The figures are on next page 

24. GRAPHS: © 2019 BHU_FILES under AMBALA COLLEGE OF ENGINEERING AND APPLIED RESEARCH | All Rights Reserved

25. Here, we have two clusters. (Note that the number of clusters is arbitrary). What do these clusters represent? It can be difficult to say. Sometimes the model finds patterns in the data that you don't want it to learn, such as stereotypes or  bias .

26. Reinforcement Learning An additional branch of machine learning is reinforcement learning (RL). Reinforcement learning differs from other types of machine learning. In RL you don't collect examples with labels. Imagine you want to teach a machine to play a very basic video game and never lose. You set up the model (often called an agent in RL) with the game, and you tell the model not to get a "game over" screen. During training, the agent receives a reward when it performs this task, which is called a reward function. With reinforcement learning, the agent can learn very quickly how to outperform humans.

27. Agent:  It is an assumed entity which performs actions in an environment to gain some reward. Environment (e):  A scenario that an agent has to face. Reward (R):  An immediate return given to an agent when he or she performs specific action or task. State (s):  State refers to the current situation returned by the environment. SOME TERMS: Clustering Clustering is typically done when labeled data is not available. This is an  unsupervised  learning problem Classification Classification requires a set of labels for the model to assign to a given item. This is a supervised learning problem. Regression Regression requires labeled numerical data. This is a supervised learning problem.

28. APPLICATIONS OF MACHINE LEARNING

29. Virtual Personal Assistants Siri, Alexa, Google Now are some of the popular examples of virtual personal assistants. As the name suggests, they assist in finding information, when asked over voice. Virtual Assistants are integrated to a variety of platforms. For example: Smart Speakers: Amazon Echo and Google Home Smartphones: Samsung Bixby on Samsung S8 Mobile Apps: Google Allo Videos Surveillance Social Media Services Email Spam and Malware Filtering Online Customer Support Product Recommendations

30. Online Fraud Detection Machine learning is proving its potential to make cyberspace a secure place and tracking monetary frauds online is one of its examples. For example: Paypal is using ML for protection against money laundering. The company uses a set of tools that helps them to compare millions of transactions taking place and distinguish between legitimate or illegitimate transactions taking place between the buyers and sellers. © 2019 BHU_FILES under AMBALA COLLEGE OF ENGINEERING AND APPLIED RESEARCH | All Rights Reserved

31. A SMALL EXAMPLE: http://localhost:8888/notebooks/CDAC%20important/week3/titanic_optimized%20BHUVAN%20CHOPRA.ipynb

32. SOURCES: https://developers.google.com/machine-learning/glossary#m https://docs.microsoft.com/en-us/azure/machine-learning/service/concept-deep-learning-vs-machine-learning https://www.google.com/search?q=deep+learning&sxsrf=ACYBGNQXqpT6_63HgZgi_ig9QEn-ZlBCaw:1573151221073&source=lnms&tbm=isch&sa=X&ved=0ahUKEwiY2tb93NjlAhVBfH0KHSG9DLEQ_AUIEygC&cshid=1573151396797265&biw=1536&bih=754&dpr=1.25#imgrc=TdQZL6LqyZk-iM: https://www.geeksforgeeks.org/best-python-libraries-for-machine-learning/

33. ANY QUERIES??