Teaching

Courses, workshops, and educational resources developed by Aditya Balu

Teaching Philosophy

My teaching philosophy centers on creating an inclusive, interactive learning environment that bridges theoretical concepts with practical applications. I believe in empowering students through hands-on experiences and real-world problem-solving, particularly at the intersection of engineering and computer science.

Courses Taught

Iowa State University

As Instructor

ME 170 – Engineering Graphics and SolidWorks (Spring 2022)

  • Introduction to engineering graphics and visualization
  • 3D modeling using SolidWorks
  • Engineering drawing standards and practices
  • Design communication and documentation

CPS 364X – Cyber-Physical Systems Applications (Spring 2023)

  • Fundamentals of cyber-physical systems
  • Integration of computation with physical processes
  • Sensing, actuation, and control in CPS
  • Applications in robotics, manufacturing, and smart infrastructure

As Teaching Assistant

ME 592X – Data Analytics and Machine Learning for Cyber-Physical Systems (Spring 2018 & Spring 2019)

  • Introduction to data analytics for engineering applications
  • Machine learning methods for CPS data
  • Predictive modeling and control
  • Real-time analytics in cyber-physical environments

ME 570X – Solid Modeling and GPU Computing (Spring 2019)

  • Advanced solid modeling techniques
  • GPU architecture and programming with CUDA
  • Parallel algorithms for engineering applications
  • Accelerated simulation and visualization

ME 324 – Manufacturing Processes (Fall 2016)

  • Fundamentals of manufacturing processes
  • Material removal and forming processes
  • Process planning and optimization
  • Quality control in manufacturing

Workshops and Tutorials

I have organized and conducted numerous workshops and tutorials to disseminate knowledge in deep learning, high-performance computing, and their applications in science and engineering:

  1. “Demystifying Trending AI Techniques”
    TrAC Tutorial, Ames, IA (April 2023)

    • Overview of diffusion models, transformers, and large language models
    • Applications in scientific computing and engineering design

  2. “A Deep Dive into Deep Learning: Architectures and Algorithms”
    Midwest Big Data Summer School, Ames, IA (May 2022)

    • Neural network fundamentals and advanced architectures
    • Training methodologies and optimization techniques
    • Hands-on implementation exercises

  3. “Intro to Cloud-based Deep Learning”
    TrAC, CyVerse and Jetstream2 Tutorial, Virtual (April 2022)

    • Setting up deep learning environments on cloud platforms
    • Scaling training with distributed computing
    • Best practices for efficient resource utilization

  4. “Scientific Machine Learning Using HPC Servers on the Cloud”
    SC21 Tutorial (2021)

    • Integration of scientific computing with machine learning
    • High-performance computing strategies for ML workflows
    • Case studies in computational science applications

  5. “Distributed Deep Learning on HPC Servers for Large Scale Computer Vision Applications”
    CVPR Tutorial (2021)

    • Scaling deep learning to multiple nodes and GPUs
    • Communication-efficient training algorithms
    • Performance optimization techniques

  6. “Implementing Deep Learning for Computer Vision Applications”
    Midwest Big Data Summer School, Ames, IA (May 2021)

    • Convolutional neural networks and vision transformers
    • Object detection, segmentation, and recognition
    • Practical implementation challenges and solutions

  7. “Intro to Deep Learning”
    Air Force Research Lab, Dayton, OH (Dec 2020)

    • Fundamentals of neural networks
    • Training methodologies and evaluation metrics
    • Applications in defense and aerospace

Educational Materials

I develop and maintain various educational resources for students and researchers:

  • GPU Computing Tutorial Series
    Comprehensive tutorial series covering CUDA programming for scientific applications
  • Deep Learning for Engineers
    Resource collection tailored to engineering students with less programming background
  • Scientific Machine Learning Repository
    Code examples and notebooks demonstrating integration of physics-based models with ML

Student Research Mentoring

I actively mentor undergraduate and graduate students in research projects related to:

  • Deep learning for engineering applications
  • Scientific machine learning
  • High-performance computing
  • Computer-aided design and manufacturing

If you are interested in research opportunities or have questions about my courses, please feel free to contact me.