Algorithmic Models and Machine Learning

Description

PRODUCT/COURSE DESCRIPTION

Over the past 10 years, machine learning has brought innovations such as self-driving
cars, speech recognition, web search, and a vastly enhanced understanding of the human
genome. The Algorithmic Models and Machine Learning course is curated to provide a
deeper introduction to concepts such as: machine learning, algorithmic models, data and
computational structures, debugging models, analyzing performance of models, designing
codes and deploying them. With over 50 hours of content, this course will provide learners
a thorough understanding of Algorithmic Models and Machine Learning and its various
concepts to help learners kick start or progress their career in this dynamic and expanding
field of study.

PREREQUISITES

• Graduate (Engineering/Technology/Statistics/Mathematics) with 2-3 Years of IT
  experience recommended
• Basic understanding of IT and programming
• Basic understanding of math and statistics

COURSE OUTLINE

The Algorithmic Models and Machine Learning course is curated to provide a deeper
introduction to concepts such as: machine learning, algorithmic models, data and
computational structures, debugging models, analyzing performance of models, designing
codes, and deploying them.
This course includes: Supervised & Unsupervised Models, Deep Learning Algorithms, Neural
Networks, Training Sets, Bayesian Model, Model Development & Deployment, Concurrency &
Parellelism, Infrastructure Automation, Tensorflo, Refactoring Algorithms, Human-centered
Software Design, Binary Trees, Graphs & Hash Data, Code Testing & Debugging, & OS
Deployment Strategies.

TOOLS USED

Python, Scikit Learn, Keras, Tensorflow, Pandas, Jupyter, Numpy, MatplotLib, H2O, Java,
PyCharm, Prospector, .Net, Visual Studio, WDK, Nuget, MDbg, PerfView, DebugDiag

LEARNING OBJECTIVES

• Differentiate between supervised and unsupervised learning algorithms and naïve and efficient algorithms
• Evaluate various data and computational structures that can be used to develop an algorithmic model
• Assess various system limitations (such as runtime, memory, and parallel programming constraints) while
  running an algorithmic model
• Evaluate the speed and memory interdependencies of a system and an algorithmic model
• Develop data flow diagrams for proposed algorithmic models
• Evaluate the runtime and memory requirements of the model
• Demonstrate the testing and debugging of sample algorithmic models
• Analyze performance indicators (such as runtime, memory usage, model efficiency, etc.) of sample
  algorithmic models
• Evaluate designs and data flow diagrams of core algorithmic models in sample autonomous systems
• Evaluate the various available resources to productionise algorithmic models
• Assess parallel programming requirements for sample algorithmic models
• Discuss the principles of code and design quality
• Discuss the importance of designing testable, version controlled and reproducible software code
• Evaluate best practices around deploying Machine Learning models and monitoring model performance
• Develop software code and automated integrations to support the deployment of sample algorithmic models
• Develop different types of test cases for the code for analyses of code performance and testing automation
• Document test case results and perform optimization of sample software code based on test results

COURSE DURATION: 60 HOURS

Theory — 38 hours Practical — 20 hours

COST

INR 20060.00