Start Date
May 2023
Duration
3 Months
Enrol Now
Book Your seat
What is this course about?
The purpose of this course is to enable learners to develop an in-depth understanding of the machine learning algorithms, principals, and techniques with a special focus on the underlying mathematics and statistics. This course will enable the learners to develop hands-on skills in the implementation of various machine learning algorithms. The learner will be able to analyze a real-world problem, design a solution and implement it using an appropriate machine learning algorithm(s).
Learning Outcomes:
On successful completion of this course the student will be able to:- Understand and appreciate the underlying issues and challenges of machine learning algorithms for implementation and application in challenging real-world scenarios.
- Analyze and relate the mathematical and statistical background of machine learning models for finding optimal solutions for the industry.
- Implement various supervised and unsupervised machine learning algorithm for dynamic real-world problems.
- Evaluate the results of a model and conclude the possible steps for evolving them into a usable application.
Become an Machine Learning
Expert in just 3 Months
Course Curriculum
- Supervised learning
- Unsupervised learning
- Cost function
- Gradient Descent (single and multi-variables)
- Normal equation
- Classification (Binary)
- Hypothesis representation
- Decision Boundary
- Cost Function
- Optimization
- Classification (Multi-Class)
- Data fitting (over fitting vs under fitting)
- Regularized Linear Regression
- Regularized Logistic Regression
- Optimization
- Margin classification
- Kernels
- K-means
- What is consensus algorithm and why it is necessary.
- Introduction to different consensus algorithms PoW, PoS, DPoS, PoH, etc.
- Practical Byzantine Fault Tolerance.
- What’s unique about Ethereum networks.
- Ethereum v1 and V2
- What’s new in Ethereum v2
- Why to reduce the dimension of a problem
- Principal component Analysis
- Principal component selection (Number of PC)
- Gaussian Distribution
- Anomaly detection system
- Multivariate Gaussian distribution
- Why we need Neural networks (Non-Linear Hypotheses)
- Model Representation
- Multiclass Classification
- Back-propagation algorithm
- Random initialization
- Model selection
- Accuracy Measures(precision and recall)
- Content Based recommendation
- Collaborative filtering
- Vectorization
- Mean normalization
- Stochastic gradient descent
- Convergence of SGD
- Introduction to MapReduce
- Project work
Entry Requirements
Basic knowledge of Python programming language is required for this course
Meet Our Trainers
Engr. Anjum Nazir
Expertise:
Cyber Security Architect, Blockchain, Linux/DevOps
Doctor of Philosophy - PhD, Computer and
Information Systems Security/Information Assurance
NUCES
Programming languages and tools
Benefits of the course
Conduct specialized research to advance current technologies
Execute Industry-specific data mining and data analysis to create more value
Understand Software design and information architecture