Rehan Machine Learning Engineer at SONY India Software
No reviews yet

I am a passionate and experienced machine learning instructor with a robust background in computer science and statistics, backed by 4 years of dedicated teaching and industry experience.

With a Master's degree in Artificial Intelligence, I have had the privilege of guiding students and professionals alike through the fascinating world of machine learning. My journey as an educator has equipped me with the skills and insights necessary to make complex topics accessible and engaging.

Over the course of my 4 year career, I have honed my ability to simplify intricate technical concepts, ensuring that learners of all backgrounds can grasp the fundamentals of machine learning. My teaching style involves creating interactive and hands-on experiences that foster deep comprehension and critical thinking.

In my courses, I emphasize the practical applications of machine learning, equipping students with the knowledge and confidence to address real-world challenges. My commitment to inclusivity and accessibility means that I strive to accommodate diverse learning needs and actively seek feedback to enhance the learning journey continuously.

Together, we embark on exciting deep-learning projects that demonstrate the incredible capabilities of this field:

1. Image Recognition: We delve into building deep learning models capable of identifying and classifying objects in images, utilizing datasets like ImageNet, COCO, or Custom Dataset.

2. Object Detection: We explore the fascinating world of object detection, training models to locate and classify objects in images or videos, leveraging COCO or the Open Images dataset.
Sentiment Analysis: We tackle text analysis, teaching deep learning models to discern sentiment in various text forms, such as social media posts or movie reviews, with datasets like IMDB or the Stanford Sentiment Treebank.

3. Translation: We venture into language translation, building models that can translate text between languages, using datasets like the Europarl corpus or the United Nations Parallel Corpus.

4. Text Generation: We unlock the power of generating text, from poetry to news articles, using datasets like the Poetry Foundation dataset or the Reuters news dataset.

5. Music Generation: We explore the art of generating music, from melodies to drum beats, with datasets like the Nottingham Music Database or the Lakh MIDI dataset.

6. Game Playing: We engage in the challenge of creating models that can master games like chess or Go, employing game records or self-play data.

7. Fraud Detection: We delve into the crucial domain of fraud detection, teaching models to identify fraudulent activities in areas such as credit card transactions or insurance claims.

8. Medical Diagnosis: We navigate the realm of healthcare by developing models that can diagnose medical conditions based on records or images.

9. Customer Segmentation: We analyze customer behavior, grouping them into segments based on characteristics, using customer data.

My mission as an instructor is to ignite curiosity and empower students to explore the limitless possibilities of machine learning. With four years of experience, I am well-prepared to guide you on this exciting journey, leveraging AI and deep learning to shape the future.

Subjects

  • Computer Vision Beginner-Expert

  • Artificial Intelligence Deep Learning Beginner-Expert

  • Deep learning with Python programming Beginner-Expert

  • Machine learning Python Beginner-Expert

  • Python and OpenCV Beginner-Expert

Experience

  • Machine Learning Engineer (Apr, 2020–Present) at Sony India Ltd, Bangalore
    Sony Alpha Camera for Marine Animal Detection:
    1. Conducted extensive research and development for models related to marine animal detection.
    2. Fine-tuned machine learning models and implemented quantization techniques to optimize model performance.
    3. Successfully integrated the developed models with Sony Alpha cameras.
    4. Utilized AWS for cloud-based computing resources and infrastructure.
    5. Implemented key-point detection algorithms to identify and track marine animals.
    6. Collaborated closely with domain experts to ensure the effectiveness of the solution.

    Sony Bravia XR for Image/Video Super-Resolution:
    1. Conducted research and training of various Super-Resolution (SR) models, including SRGAN, ESRGAN, SRResNet, and SwinIR, using PyTorch on multi-GPUs.
    2. Employed Docker for model deployment, making the solution scalable and efficient.
    3. Evaluated the performance of SR models using metrics such as PSNR (Peak Signal-to-Noise Ratio) and SSIM (Structural Similarity Index).
    4. Collaborated on advancements in Single Image Super-Resolution (SISR) and Video Super-Resolution (VSR) techniques.
    5. AI/ML CV Research Paper Reproduction POC:
    6. Conducted a Proof of Concept (POC) for reproducing an AI/ML research paper in the field of computer vision.
    7. Independently implemented the research paper's methods and models to validate and verify the original findings.

    Quantization MLOPS Generative Model (GAN):
    1. Worked on quantization techniques for generative models, particularly Generative Adversarial Networks (GANs).

    CNN Architecture Docker/Kubernetes:
    1. Leveraged Docker and Kubernetes for containerization and orchestration of deep learning models, ensuring efficient and scalable deployment.

    Automatic Vehicle Offence Detection & Reporting:
    1. Developed an automatic vehicle offense detection and reporting system using deep learning models like YOLO (You Only Look Once) and Faster R-CNN.
    2. Enabled real-time video analysis for the detection of license plates and utilized OCR (Optical Character Recognition) for license plate number recognition.

    Auto Descriptive Video Generation Deep Learning:
    1. Conducted research and development in the field of Auto-Descriptive Video Generation using deep learning techniques.
    2. Explored the use of Generative Adversarial Networks (GANs), Autoencoders, and Recurrent Neural Networks (RNNs) to generate descriptive videos.
    3. Successfully trained, fine-tuned, and integrated models to achieve optimal results in video generation.

Education

  • Master in Machine Learning (Feb, 2021–Aug, 2022) from Bits Pilani–scored 100
  • B.Tech (Jul, 2016–Aug, 2020) from Ambedkar Institute of Advance Communication Technologies and Research Govt of NCT of Delhi–scored 8.2

Fee details

    ₹12,000–18,000/month (US$142.11–213.17/month)

Courses offered

  • Machine Learning

    • US$250
    • Duration: 2 months
    • Delivery mode: Online
    • Group size: Individual
    • Instruction language: English
    • Certificate provided: Yes
    Month 1: Foundations of Machine Learning

    Week 1: Introduction to Machine Learning

    Understand what machine learning is and its applications.
    Explore different types of machine learning (supervised, unsupervised, reinforcement learning).
    Set up Python and essential libraries (NumPy, Pandas, Matplotlib).
    Week 2: Data Preprocessing

    Data cleaning and handling missing values.
    Feature scaling and normalization.
    Categorical data encoding (one-hot encoding).
    Data splitting (training, validation, and test sets).
    Week 3: Supervised Learning - Regression

    Introduction to regression.
    Linear regression.
    Polynomial regression.
    Model evaluation (MSE, R-squared).
    Week 4: Supervised Learning - Classification

    Introduction to classification.
    Logistic regression.
    K-Nearest Neighbors (KNN).
    Model evaluation (accuracy, precision, recall, F1-score).
    Month 2: Advanced Machine Learning

    Week 5: Decision Trees and Random Forests

    Decision tree basics.
    Random Forests for ensemble learning.
    Feature importance and visualization.
    Week 6: Unsupervised Learning - Clustering

    Introduction to clustering.
    K-Means clustering.
    Hierarchical clustering.
    Evaluating clustering results.
    Week 7: Dimensionality Reduction

    Principal Component Analysis (PCA).
    t-Distributed Stochastic Neighbor Embedding (t-SNE).
    Week 8: Introduction to Neural Networks

    Basics of artificial neural networks (ANNs).
    Building a simple feedforward neural network using TensorFlow or PyTorch.
    Training neural networks and adjusting hyperparameters.
    Week 9: Deep Learning

    Introduction to deep learning.
    Convolutional Neural Networks (CNNs) for image recognition.
    Recurrent Neural Networks (RNNs) for sequence data.
    Week 10: Final Projects and Capstone

    Work on a machine learning project of your choice.
    Apply concepts learned throughout the course.
    Prepare and present your project to the class.
    Week 11: Model Deployment and Scaling

    Deploy a machine learning model using Flask or a similar framework.
    Discuss model scaling and production considerations.
    Week 12: Ethical and Future Considerations

    Explore ethical considerations in machine learning.
    Discuss emerging trends and future directions in the field.

    Throughout the course, students will work on practical exercises, assignments, and projects to reinforce their understanding of machine learning concepts and gain hands-on experience.

  • Deep Learning || TensorFlow || PyTorch

    • US$300
    • Duration: 2-3 months
    • Delivery mode: Online
    • Group size: Individual
    • Instruction language: English
    • Certificate provided: Yes
    Month 1: Foundations of Deep Learning with TensorFlow

    Week 1-2: Introduction to Deep Learning and TensorFlow

    Understand what deep learning is and its applications.
    Introduction to TensorFlow and its ecosystem.
    Building and training simple neural networks with TensorFlow.
    Week 3-4: Convolutional Neural Networks (CNNs)

    Learn about CNNs and their role in image recognition.
    Implement CNNs using TensorFlow for image classification.
    Fine-tuning pre-trained models like VGG16 or ResNet.
    Week 5-6: Recurrent Neural Networks (RNNs)

    Introduction to RNNs and their applications in sequential data analysis.
    Implement RNNs and LSTMs (Long Short-Term Memory) with TensorFlow for tasks like sequence prediction and text generation.
    Week 7-8: Generative Adversarial Networks (GANs)

    Explore the fundamentals of GANs and their applications in image generation.
    Implement GANs with TensorFlow for tasks like image-to-image translation or generating realistic images.
    Month 2: Advanced Deep Learning with PyTorch

    Week 9-10: Transition to PyTorch

    Introduction to PyTorch and its dynamic computation graph.
    Porting TensorFlow models to PyTorch.
    Understanding PyTorch tensors and autograd.
    Week 11-12: Advanced Topics in Deep Learning with PyTorch

    Dive deeper into PyTorch's capabilities and flexibility.
    Explore PyTorch's custom layers and modules.
    Building and training complex neural networks in PyTorch.
    Week 13-14: Natural Language Processing (NLP) with Transformers

    Introduction to Transformers architecture.
    Implement Transformers-based models like BERT or GPT-2 for NLP tasks.
    Fine-tuning pre-trained NLP models for specific tasks.
    Week 15-16: Reinforcement Learning with PyTorch

    Introduction to reinforcement learning (RL).
    Implement RL algorithms like Q-learning or Deep Q-Networks (DQN) with PyTorch.
    Solve RL environments and games.
    Week 17-18: Deployment and Model Serving

    Learn how to deploy deep learning models using Flask, FastAPI, or other web frameworks.
    Discuss model serving options like TensorFlow Serving or TorchServe.
    Week 19-20: Capstone Project and Real-world Applications

    Work on a deep learning project of your choice.
    Apply concepts learned throughout the course.
    Prepare and present your project to the class.

  • Python -> Machine Learning -> Deep Learning --> AWS

    • US$500
    • Duration: 4-5 Months
    • Delivery mode: Online
    • Group size: Individual
    • Instruction language: English
    • Certificate provided: Yes
    Month 1: Python Fundamentals (4 weeks)

    Week 1-2: Python Basics

    Introduction to Python.
    Variables, data types, and operators.
    Control structures (if, loops).
    Functions and modules.
    Week 3: Data Structures

    Lists, tuples, and dictionaries.
    Sets and strings.
    List comprehensions.
    Week 4: Advanced Python

    Object-oriented programming (OOP).
    Exception handling.
    File handling.
    Month 2: Machine Learning (4 weeks)

    Week 1-2: Introduction to Machine Learning

    What is machine learning?
    Types of machine learning.
    Supervised vs. unsupervised learning.
    Week 3-4: Hands-on with Scikit-Learn

    Exploratory data analysis (EDA).
    Data preprocessing.
    Building and evaluating machine learning models with Scikit-Learn.
    Month 3: Deep Learning with PyTorch (4 weeks)

    Week 1-2: Introduction to Deep Learning

    Basics of neural networks.
    Introduction to PyTorch.
    Week 3-4: Building Deep Learning Models

    Convolutional Neural Networks (CNNs) for image data.
    Recurrent Neural Networks (RNNs) for sequence data.
    Introduction to transfer learning.
    Month 4: AWS and Deployment (4 weeks)

    Week 1-2: AWS Fundamentals

    Introduction to Amazon Web Services (AWS).
    Setting up an AWS account.
    Overview of core AWS services (EC2, S3, RDS).
    Week 3-4: Deploying Machine Learning Models on AWS

    Creating an EC2 instance.
    Deploying machine learning models using Flask.
    Scalability and load balancing.
    Data storage and management on AWS S3.
    Throughout the 4 Months: Projects and Practice

    Work on machine learning and deep learning projects to apply what you've learned.
    Collaborate with peers on projects to gain practical experience.
    Continuously practice Python programming and data manipulation.
    Regularly review and practice AWS concepts.
    Additional Notes:

    This plan assumes you have a basic understanding of programming concepts.
    Regularly consult online resources, tutorials, and documentation for each topic.
    Consider taking online courses or reading books on each subject to supplement your learning.
    Attend webinars or workshops to stay updated on the latest developments in machine learning and AWS.
    This plan provides a structured path to acquire fundamental skills in Python, machine learning, deep learning, and AWS in four months. Keep in mind that learning pace may vary from person to person, so adjust the schedule accordingly to ensure a thorough understanding of each topic.

  • Computer Vision using Deep Learning

    • US$300
    • Duration: 2 months
    • Delivery mode: Online
    • Group size: Individual
    • Instruction language: English
    • Certificate provided: Yes
    Month 1: Foundations of Computer Vision and Deep Learning

    Week 1-2: Introduction to Computer Vision

    Understand the basics of computer vision.
    Learn about key concepts like image processing, feature extraction, and object detection.
    Explore real-world applications of computer vision.
    Week 3-4: Python and Libraries

    Get comfortable with Python programming.
    Familiarize yourself with essential libraries: NumPy, OpenCV, and Matplotlib.
    Learn how to manipulate and visualize images using these libraries.
    Week 5-6: Introduction to Deep Learning

    Understand the fundamentals of deep learning.
    Learn about neural networks, activation functions, and backpropagation.
    Implement a basic neural network using a deep learning framework like TensorFlow or PyTorch.
    Week 7-8: Convolutional Neural Networks (CNNs)

    Dive into CNNs, the backbone of computer vision.
    Study CNN architectures and layers (convolution, pooling, fully connected).
    Implement a CNN for image classification tasks using TensorFlow or PyTorch.
    Month 2: Advanced Computer Vision with Deep Learning

    Week 9-10: Object Detection

    Learn about object detection techniques (e.g., Faster R-CNN, YOLO).
    Implement object detection models using pre-trained networks.
    Explore applications like real-time object detection.
    Week 11-12: Image Segmentation

    Understand image segmentation techniques (e.g., U-Net, Mask R-CNN).
    Implement image segmentation models for tasks like semantic and instance segmentation.
    Week 13-14: Transfer Learning and Fine-Tuning

    Learn about transfer learning and its importance in computer vision.
    Fine-tune pre-trained models for specific tasks.
    Explore domain adaptation techniques.
    Week 15-16: Advanced Topics

    Dive into advanced topics such as neural style transfer, image generation (GANs), and image captioning.
    Explore cutting-edge research and applications in computer vision.
    Throughout the 2 Months: Projects and Practice

    Work on computer vision projects to apply your knowledge.
    Practice with real datasets and challenges.
    Collaborate with peers or join online competitions to enhance your skills.
    Additional Tips:

    Regularly consult online resources, tutorials, and documentation for each topic.
    Consider taking online courses or reading books on computer vision and deep learning.
    Experiment with different datasets and projects to gain practical experience.
    Attend webinars or workshops to stay updated on the latest developments in computer vision.
    Remember that computer vision is a vast field, and two months will provide you with a solid foundation. Continue learning and experimenting beyond this plan to further deepen your expertise in computer vision using deep learning techniques.

  • Generative Model with Deep Learning || PyTorch

    • US$300
    • Duration: 2 months
    • Delivery mode: Online
    • Group size: Individual
    • Instruction language: English
    • Certificate provided: Yes
    Month 1: Foundations of Generative Models

    Week 1-2: Introduction to Generative Models

    Understand what generative models are and their applications.
    Explore different types of generative models, including Variational Autoencoders (VAEs) and Generative Adversarial Networks (GANs).
    Week 3-4: Python and Libraries

    Brush up on Python programming if needed.
    Familiarize yourself with essential libraries: NumPy, Matplotlib, and TensorFlow/PyTorch (choose one).
    Learn how to manipulate data and create basic neural networks.
    Week 5-6: Variational Autoencoders (VAEs)

    Dive into Variational Autoencoders (VAEs), a probabilistic generative model.
    Implement a VAE for image generation using TensorFlow or PyTorch.
    Study the mathematics behind VAEs, including the loss functions and sampling.
    Month 2: Generative Adversarial Networks (GANs) and Projects

    Week 7-8: Generative Adversarial Networks (GANs)

    Learn about Generative Adversarial Networks (GANs) and their architecture.
    Implement a simple GAN for image generation.
    Study GAN variants like DCGAN, WGAN, and CGAN.
    Week 9-10: Project Selection

    Choose a generative modeling project based on your interests. Options include image generation, text generation, or music generation.
    Plan your project, including dataset selection and model architecture.
    Week 11-12: Project Implementation and Fine-Tuning

    Start working on your generative modeling project.
    Implement the chosen GAN or VAE variant.
    Fine-tune your model and experiment with hyperparameters.
    Week 13-14: Project Evaluation and Documentation

    Evaluate your generative model using appropriate metrics.
    Create documentation for your project, including a README file that explains how to use and reproduce your model.
    Consider creating visualizations or generating samples to showcase your model's capabilities.
    Throughout the 2 Months: Projects and Practice

    Dedicate a significant amount of time to your project to gain hands-on experience.
    Collaborate with peers, join online communities, or seek mentorship for guidance and feedback.
    Continuously practice and experiment with generative models to deepen your understanding.
    Additional Tips:

    Stay updated with the latest research papers and developments in generative modeling.
    Seek help from online tutorials, courses, or forums when facing challenges during your project.
    Attend webinars, workshops, or meetups related to generative models to expand your knowledge.
    Remember that generative modeling can be complex, and it may take time to fine-tune your model and achieve desired results. Focus on learning and experimentation, and use your project as an opportunity to apply what you've learned in a practical context.

  • MLOPS with AWS

    • US$350
    • Duration: 2-3 months
    • Delivery mode: Online
    • Group size: Individual
    • Instruction language: English
    • Certificate provided: Yes
    Month 1: MLOps Fundamentals and Setting Up

    Week 1-2: Introduction to MLOps

    Understand what MLOps is and its importance in machine learning.
    Learn about key concepts like version control, continuous integration (CI), and continuous delivery (CD) in the context of machine learning.
    Week 3-4: Setting Up Your Environment

    Set up a development environment with Python, Jupyter Notebooks, and relevant libraries (NumPy, Pandas, Scikit-Learn).
    Familiarize yourself with Git for version control.
    Explore cloud platforms like AWS, Azure, or Google Cloud for hosting your machine learning projects.
    Week 5-6: Containerization with Docker

    Learn about Docker and containerization.
    Create Docker containers for your machine learning projects.
    Understand the benefits of containerization in MLOps.
    Month 2: Building MLOps Pipelines and Automation

    Week 7-8: Continuous Integration and Continuous Delivery (CI/CD) for ML

    Set up CI/CD pipelines for your machine learning projects using tools like Jenkins, GitLab CI/CD, or Travis CI.
    Automate the testing and deployment of machine learning models.
    Practice versioning models and data.
    Week 9-10: Model Monitoring and Management

    Implement model monitoring and logging using tools like Prometheus and Grafana.
    Explore model versioning and management systems like MLflow.
    Learn about model drift detection and handling concept.
    Week 11-12: Orchestration and Scalability

    Implement orchestration of machine learning workflows with tools like Apache Airflow or Kubeflow Pipelines.
    Explore container orchestration with Kubernetes.
    Scale your machine learning applications as needed.
    Throughout the 2 Months: Projects and Practice

    Apply MLOps practices to your machine learning projects.
    Collaborate with peers or join MLOps communities to share insights and best practices.
    Continuously improve and refine your MLOps pipelines.
    Additional Tips:

    Read books and articles on MLOps and DevOps principles.
    Enroll in online courses or certification programs focused on MLOps.
    Attend webinars, conferences, or workshops related to MLOps to stay updated on industry trends and best practices.
    MLOps is a broad field, and this plan provides a foundation for understanding and implementing MLOps principles and practices. Keep in mind that mastering MLOps is an ongoing process, and the two months will give you a solid start on your journey to efficient and automated machine learning operations.

Reviews

No reviews yet. Be the first one to review this tutor.