Mathematics for Machine Learning - Il Course Code: 22480 Program Name: Diploma in Artificial Intelligence and Machine Learning Program Code: AN Semester : Fourth Course Title : Mathematies for Machine Learning - I Course Code 222480 1, RATIONALE Machine learning is important because it gives enterprises a view of trends in customer behavior ‘and operational business patterns, as well as supports the development of new products. Machine learning and deep learning (DL) are subsets of Al. This course represents an important evolution in computer science and data processing that is quickly transforming, a vast array of industries. Atificial intelligence generally refers to processes and algorithms that are able to simulate human intelligence, including cognitive functions such as perception, learning and problem solving. 2. COMPETENCY The aim of this course is to help the student to attain the following industry identified competency through various teaching learning experiences: Study of the required data, analyze it and accordingly create @ problem and solution algorithms. 3. COURSE OUTCOMES (COs) The theory, practical experiences and relevant soft skills associated with this course are to be taught and implemented in Python / R programming language, so that the student demonstrates the following industry oriented COs associated with the above mentioned competency . Implement the given problem based on calculus. Implement real life problems using matrices concepts. Build programs to implement basic operations based on vectors and tensors. Implement methods based on the interpolation concept Evaluate numerical integration and differentiation functions. Apply the linear programming problem concept to obtain optimal solution . measee 4. TEACHING AND EXAMINATION SCHEME Examination Seheme Theory | |p| crete | Paper [ESE [PA [Tour [ese RyryP (LATSP) | Hrs, lax |Min |Max Min Max | Min |Max a & [3 [| 2 [aor] 0 | 00 [ao [asa] vo | 25 (*): Under the theory PA; Out of 30 marks, 10 marks of theory PA are for micro-project MSBTE — Final Copy Dt. 10.01.2023 Page oF)‘Mathematics for Machine Learning - I. Course Code: 22480 10 be taken during the semester for the assessment of the UOs required for the attainment of the Cos, Legends: L-Lecture; T ~ Tuorial/Teacher Guided Theory Practice; P -Practical; C — Credit, ESE -End Semester Examination; PA - Progressive Assessment, 5. COURSE MAP COURSE MAP(with sample COs, PrOs, UOs, ADOs and topics) This course map illustrates din overview of the flow and linkages of the topics at various levels of ‘outcomes (details in subsequent sections) to be attained by the student by the end of the course, in all domains of learning in terms of the industry/employer identified competency depicted at the centre of this map 06H nie deat en sao iF nn) ail EER, aa” oN soon tiie? | 4 an) “Moin nas > A, Serie eon gee Als Rie, — MSBTE - Final Copy Dt. 2023, Page 2 of 9Mathematics for Machine Learning - IL Course Code: 22480 6. SUGGESTED PRACTICALS/ EXERCISES ‘The practical’s in this section are PrOs (i.e. sub-components of the COs) to be developed and assessed in the student for the attainment of the competence: ., | Approx. z Practical Outcomes (PrOs) > Hrs. 7 | Required Write a program to compute partial derivatives eg: package Deriv, 1 P 1 2 part deriv 0, 2 | Write a program to find the maxima and minima for two variables, | 1 2 Write a program to find 5 (a) Write a program based on Elementary Row and column fl i transformation using R/Python loops. (b) Rank of a matrix. 4 _ | Write a program to solve system of linear equations. I 2 Write a program to calculate Eigen values for given matrix of order2 |) oe & 3 and Eigen vector for given matrix of order 2. Write a program to implement Algebra of vectors like 6 (a) addition, subtraction, scalar multiplication. Mm 4 (b) dot product, cross product, scalar triple produ | 7 _ | Write a program to implement basic algebraic operations on Tensors |, ms like addition, subtraction and rank of Tensors. Write a Program to interpolate using newton forward interpolation. [IV 2 Write @ Program to interpolate using newton backward interpolation. | py 2 19 _| Write a program for the implementation of Vv y 2 Linear extrapolation using extrapolate(). ei Z 11 _ | Write a program to evaluate numerical differentiation and for the Vv 7 given data, 12_| Weitea program to evaluate numerical integration using Trapezoidal | \, 7 rule/ Simipson’s one third Rule for the given data. r 13 _| Write a program to build Mathematical formulation of LPP for the | yy mo given data, 14 _| Write a program to implement comer point method / Simplex method |”, om for 2 equations in 2 variables and represent it graphically. 15_| Write a program to find the maxima and minima for three variables. | 1 2 16 _| Write a program to calculate Eigen vector for given matrix of order 3 | IL 2 - Total 32 Note: +A suggestive list of PrOs is given in the above table, More such PrOs cam be added to attain the COs and competency. The practicals marked as “*’ are compulsory, so tht the student reaches the ‘Application Level’ of Bloom's Taxonomy’ as generally required by the industry. *Pracicals Marked as * are Compulsory. Other practicals can be given to fast learners/Bright students +The ‘Process’ and ‘Product’ related skills associated with each PrO are to be assessed according to 4 suggested sample given below: S.No. Performance Indicators Weightage in Yo a | Correctness of analyzing the problem statement * MSBTE — Final Copy Dt. 10.01.2023 Page 3 0f9 30 2 eH iMathematis for Machine Learning - I Course Code: 22480 | b_| Correctness of building the logic - | 40 ¢ | Debugging ability : 7 10 d__| Correctness of evaluation of the mathematical problems en) © | Ontime submission _ 10 Tot 100 | The above PrOs also comprise of the following social skills/attitudes which are Affective Domain Outcomes (ADOs) that are best developed through the laboratory/field based experiences: Handle R/Python Programming environment. Experiment with R/Python Programming environment. Import, construct, compile, debug, test and execute R/Python programs. Handle linear algebraic problems. Manage R / Python packages. Follow ethical and safe pra s. The ADOs are not specific to any one PrO, but are embedded in many PrOs. Hence, the acquisition of the ADOs takes place gradually in the student when s/he undertakes a series of practical experiences over a period of time. Moreover, the level of achievement of the ADOs according to Krathwohi's ‘Affective Domain Taxonomy’ should gradually increase as planned below: + ‘Valuing Level’ in 1* year + ‘Organizing Level’ in 2 year and + ‘Characterizing Level’ in 3" year. 7. MAJOR EQUIPMENT/ INSTRUMENTS REQUIRED ‘The major equipment with broad specification mentioned here will usher in uniformity in conduet of experiments, as well as aid to procure equipment by authorities concemed. Sr. | No. | + | Computer system (Any computer system which is available in laboratory with minimum 2GB RAM) ee ee + [Any compatible open source tools (e-z. RStudio, Eclipse, PyCharm, Eric ete.) | Equipment Name with Broad Specifications 8. UNDERPINNING THEORY COMPONENTS. Exp. | Sr.No. All ‘The following topies/subtopics should be taught and assessed in order to develop UOs in cognitive domain for achieving the COs to attain the identified competency. MSBTE — Final Copy Dt. 10.01.2023 Page 4 oro—— Mathematics for Machine Learning - 11 Course Code: 22480 Unit Unit Outcomes (UOs) ‘Topies and Sub-topies (in cognitive domain) Unit -1 lla. Calculate partial derivative of | 1.1 Introduction to Derivative and Caleulus first order, second order and | Integration mixed order 1.2 Partial derivative (Two variables ) Pr Caen msisant | 1. atin 1.2.2 Partial derivative of first order, function lic. Find maximum and second order and mixed order. ne 1.2.3 Maxima and minima of function minimum value of the " function subject to given (Two variables) ay 8 5 ; 1.2.4 Lagrange’s method of condition using Lagrange’s oe undermined multipliers. undetermined multipliers with ‘one constraint (Two variables) Unit-T1 Ba. Reduce the matrix to echelon 2.1 Introduction to types of mati , algebra Matrices form and normal form, of matrix 2.2 Elementary transformation of matrices 2b. Find the inverse of matrix by | 2.2.1 Elementary Row and column elementary transformation . transformation 2.2.2 Conversion of matrix to echelon ¥e. Calculate the rank of matrix form and Normal. form using determinant of order 22.3 Inverse of matrix using elementary and 3 transformation b4 Rank of matrix Pd. Calculate rank of matrix by | 2.4.1 Rank of matrix of order two & three reducing matrix to echelon 2.4.2 Rank of matrix by reducing matrix form and normal form to echelon form & normal form. P.5 Consistency of linear equation and their fe. Check the Consistency of solution non homogenous and 2.5.1 System of Linear equation homogenous system of a) Non Homogeneous Tinear equation using rank of b) Homogeneous matrix 2.5.2 Consistency of system of linear equation using rank of matrices. f. Calculate solution of Non 2.5.3 Solution of non Homogeneous: homogeneous and system of equation having homogenous system of linear 2) unique solution equation b) infinite number of solution 2.5.4 Solution of Homogeneous system of Pg. Find characteristic equation having polynomial . a) unique or trivial solution b) infinite number of non trivial solution h. Find eigenvalues for the 2.6 Eigen values given matrix of order 2.and 3 |" 2.6.1 Bigen values and Characteristics of Findiele _ Eigen values of matrix * Geovmmvis oroderino, | 242 Eitrveueonarixfower2 ani 10.01.2023, Page 5 of 9Mathematics for Machine Learning - Hl Course Code: 22480 Unit- 11 Vectors and ‘Tensors Uni Interpolation 3. 38. 4b. de. Solve examples on different | 3a, 3b, 3e. 3e. Calculate the magnitude, unit vector, direction ratio, direction cosines of given vector Find the position vector of point which divide the joining of two point — internally and externally d dot product , angle between two vectors, projection of one vector on another vector. Find cross product, scalar ple product . State types of tensor \d order, rank and solve algebraic operations on ‘Tensor "| 4a. Solve problems using Lagrange’s interpolation formula Construction of forward and backward difference table a) Characteristic polynomial ) Chatacteristic Equation ©) Characteristic Root 2.7 Eigen-vector matrix of order two 3.1, Introduction 3.2. Definition of scalar and vector quantity 3.3. Some basic concept : Representation of vector, Magnitude of vector , Component of vector , Direction ratio , Direction cosines 3.4. Types of vectors ~zero vector , Unit vector , Position vector, Equal vector, Negative vector. Parallel vector, Co- initial vector, Collinear vector 3.5, Algebra of vector: 3.5.1 Addition of vector a) Triangle law of vector addition b) Parallelogram law of vector addition. 3.5.1 Subtraction of vector. 3.5.2 Multiplication of vector by scalar 3.6 Product of two vector 3.6.1 Scalar (dot) product of Two ‘Vector 3.6.1.1 Projection of one vector on another vector. Angle between two vector 3.6.2 Vector (cross)product of two Vector 3.6.3 Scalar triple product of vector 3.7 Tensor 3.7.1 Definition of tensors 3.7.2 Types of tensors 3.7.3 Rank of tensors 3.7.4 Algebra of tensors 4.1 Introduction 4.2.Lagrange’s interpolation formula for missing values 4.3.Finite differences 4.3.1 . Forward difference ig; tl, [e; MSBTE— Final Copy Dt. 10.01.2023 Page 60f9 ale a e 4.3.2. Backward diff ee (GOARO OF ® [SfMathem tics for Machine Learning - I types of operators. 4d. Solve problems on forward and backward interpolation 4e. Solve problems on extrapolation find missing, function value . Course Code: 22480 43.3. Shift operator 4.3.4 Inverse shift operator 4.3.5 . Relation between forward , backward , shift and inverse shift operator 4.4.Newton’s forward and backward difference Interpolation Formula, 4.5.Concept of Extrapolation LPP Using point corner method 6c. Find optimal solution of LPP Using Simplex metho Unit -V ind First order derivative | 5.1 Introduction to numerical differentiation Numerical using forward and and integration. Differentiatio backward, 5.2.Derivative using forward and backward nand interpolation interpolation Integration | 5b. Find the area Using a ‘Trapezoidal and Simpson's | 53, Numerical integration one third rule. 5.3.1 Trapezoidal rule 5.3.2 Simpson’s one third Rule Formula Unit VI 6a. Formulate given problems | 6.1 Introduction Linear in 6.2 Mathematical formulation of LPP programming LPP 6.3 Graphical method to solving LPP Problems 6b. Find optimal solution of problems- Corner point method (Two equation in two variable ) 6.4 Optimal solution for LPP using simplex method (Two equation in two variable ) Note: To attain the COs and competency, above listed UOs need fo be undertaken (0 achieve the “Application Level’ of Bloom’s ‘Cognitive Domain Taxonomy’. 9. SUGGESTED SPECIFICATION TABLE FOR QUESTION PAPER DESIGN i ano |_Dis = Unit Title Feveing R o ours | Level | Level | Level | Marks 1 | Partial Derivatives 08 o2 | o4 | o4 10 T1_| Matrices io @ | 02 | 1 | 20 IIl_| Vectors and “Tensors 10 02 | 04 | os 4 [_1V__ [interpolation 08 o2 {04 | o4 | 10 y_ | Numerical differentiation and oa wo | oo | os integration - VI_| Linear programming problems (LPP) 04 oo | 04 | 04 | 08 Total [48 os [22 | 40 | 70 Legends: R=Remember, U=Understand, A~Apply and above (Bloom's Revised taxonomy) Note: This specification table provides general guidelines 10 assist students for their learning and to teachers to teach and assess students with respect to attainment of LOs, The actual MSBTE Final Copy Dt. 10.01.2023 Page? of 9 | TSe Code: 22480 Mathematics for Machine Learning - It Cou distribution of marks at different taxonomy levels (of R, U and A) in the question paper may vary from above table. 10. SUGGESTED STUDENT ACTIVITIES Other than the classroom and laboratory learning, following are the suggested student-related co- curricular activities which can be undertaken to accelerate the attainment of the various outcomes in this course: Students should conduct following activities in group and prepare reports of about 5 pages for each activity, also collect/record physical evidences for their (student’s) portfolio which will be useful for their placement interviews: + Prepare journal of practical. + Undertake micro-projects 11. SUGGESTED SPECIAL INSTRUCTIONAL STRATEGIES (if any) These are sample strategies, which the teacher can use to accelerate the attainment of the various outcomes in this course: * Massive open online courses (MOOCs) may be used to teach various topies/sub topics. * ‘L" in item No, 4 docs not mean only the traditional lecture method, but different types of teaching methods and media that are to be employed to develop the outcomes. + About 15-20% of the topics/sub-topics which is relatively simpler or descriptive in nature is to be given to the students for self-directed learning and assess the development of the COs through classroom presentations (see implementation guideline for details) + With respect to item No.10, teachers need to ensure to create opportunities and provisions for co-curricular activities ferent Audio Visual media for Concept understanding, + Guide student(s) in undertaking micro-projects, + Demonstrate students thoroughly before they start doing the practice. + Ensure use of latest version of tools. + Encourage students to refer various web sites to have detail understanding of JSP and related concepts. + Encourage students to refer different web-applications to have deeper understanding of web-applications, * Observe continuously the performance of students in laboratory. 12. SUGGESTED MICRO-PROJECTS Only one micro-project is planned to be undertaken by a student that needs to be assigned to him/her in the beginning of the semester. In the first four semesters, the micro-project are group- based. However, in the fifth and sixth semesters, it should be preferably be individually undertaken to build up the skill and confidence in every student to become problem solver so that ihe contributes to the projects of the industry. In special situations whe formed for micro-projects, the number of students in the group should not exceed three. The micro-project could be industry application based, internet-based, workshop-based, laboratory-based or field-based. Each micro-project should encompass two or more COs which are in fact. an integration of PrOs, UOs and ADOs. Each student will have to main work diary consisting of individual contribution in the project work and give a seminar presentation of it before submission. The total duration of the micro-project should not be less than 16 (sixteen) student engagement hours duti 1 to submit micro-pruject by the end of the semester to develop the industry oriented COs. in dated the course, The student oug Final Copy Dt. 10.01.2023 Page 8 0F9)Mathematics for Machine Learning - 1 Course Code: 22480, A suggestive list of micro-projects is given here, Similar micro-projects could be added by the concemed faculty: Develop an TensorFlow. Develop Sales Forecasting with any mart (Megamart.walmart etc.) Stock price predictions. Time Series Forecasting GUIDELINES FOR DEVELOPING MICRO PROJECTS: (Implement following relevant guideli + Must implement concepts of Python / R. es for ‘0 projects) * Must evaluate the mathematical operations studied in the theory lectures, 13. SUGGESTED LEARNING RESOURCES: Title of Book Author Publi Higher Engineering Mathematics H.K.Dass, Er.Rajnish Verma S. Chand Technical ISBN: 9788121938907, 9788121938907 Higher Engineering Tata Megraw Hill Education ‘Mathematics ‘Advanee Engine Mathematics ERWIN KREYSZIG 2 BV Ramana private limited , New Delhi iaihemalise ISBN : 9780070634190 Higher Engineetin Khanna Publishers igher Engi 8 B.S Grewal ISBN-10. 9788193328491 ISBN-13. 978-8193328491 Wiley India Pvt Lid ISBN : 0470458364 Engineering athematics Ravish R singh Tata Megraw Hill Education private limited , New Delhi ‘Tutorial Approach Mukul Bhast tei Engineering Pearson 6 | Fpgineering Babu Ram ISBN : 8131726916, ies 9788131726914 14. SOFTWARE/LEARNING WEBSITES a. https:/ww datacamp.com/utorial/machine-learning-in-r b._ https://steelkiwi.com/blog/python-for-ai-and-machine-learning ec. hutpsi/fewthomas.github.io/docs d._ https://course.ces.neu.edu ce. https:/Avww.freecodecamp.org MSBTE— Final Copy Dr. 10.01.2023 Page of