CNNs in Product Quality Evaluation

Tapping into Deep Learning for Superior Product Inspection and Validation

  • Schedule

    20 – 22 August 2024

    09.00 – 15.00 (WIB)

  • Investment

    Rp. 5.550.000


Hours Course




In this workshop, participants will dive into the world of deep learning, specifically exploring Convolutional Neural Networks (CNNs) for enhanced product quality evaluation. Beginning with Python essentials and data manipulation using Pandas, the course swiftly progresses to neural network basics—covering layers, neurons, and activation functions. The focal point is CNNs, with a focus on convolutional concepts, architecture, and practical applications. A hands-on case study guides participants through image data loading, data augmentation, model training, and evaluation.

By course’s end, participants will master CNNs, gaining the skills to revolutionize product inspection using deep learning techniques. This concise, practical journey integrates Python proficiency, neural network principles, and real-world application in product quality assessment.

Course Syllabus

  • Working with Conda Environment: Understand the Conda environment and its role in managing dependencies for Python projects.
  • Introduction to Python for data science: Familiarize yourself with Python’s fundamentals and its application in data science tasks.
  • Data manipulation and processing with Python Pandas: Explore Pandas library for efficient data manipulation and processing, a crucial skill for handling datasets in deep learning projects.
  • Layer and neurons: Delve into the foundational components of neural networks, understanding the structure and function of layers and neurons.
  • Activation and cost function: Explore activation functions and cost functions, crucial elements in determining the output and optimizing neural network performance.
  • Feedforward: Grasp the concept of feedforward propagation, the fundamental process by which neural networks make predictions.
  • Backpropagation: Understand the backpropagation algorithm, a key mechanism for adjusting the network’s weights during the training process.
  • Convolution concept: Explore the fundamental concepts of convolution in CNNs, including kernels, strides, padding, and filters.
  • Convolutional Neural Network Architecture: Gain insights into the overall architecture of Convolutional Neural Networks, focusing on how convolutional layers are organized for effective feature extraction.
  • Load the data images and apply data augmentation techniques: Learn to load image data and apply data augmentation methods to enhance the diversity and size of the training dataset.
  • Visualize the images: Utilize visualization techniques to gain insights into the characteristics of the image data.
  • Training with validation: Walk through the entire process of training a CNN model, from defining the architecture to evaluating its performance on a validation set.
  • Testing on unseen images: Apply the trained model to test on new, unseen images for real-world product quality inspection.
  • Model logging and audit using Tensorboard: Explore how to log and audit the model using Tensorboard, providing insights into the training process and performance metrics.

Course Receivables:

  • Lecturer’s Notes

    Including Course Books (PDF), HTML files, course transcripts (if any).

  • Highly-accelerated Learning

    Learn under the assistance of mentorship of our lead instructor and a band of qualified teaching assistants throughout each course.

  • Certification of Completion

    Show current employer hat you’ve completed the course with a signed certificate of completion.

  • Quality Learning Environment

    We pay meticulous attention to the logistical details of our workshops: quality audio and visual setups, comfortable sitting arrangements, and small group size.

  • Refreshments & Coffee Break

    In our commitment to delivering a premium experience, we collaborate with leading catering services in Jakarta. Our aim is to ensure that all participants are served delectable lunches and revitalizing coffee breaks.


Courses in this series cater to a diverse audience: from casual learners and working professionals to those venturing into data science and machine learning without a programming background.

We recognize that many students may not have prior expertise in statistics, mathematics, or algebra. Therefore, our courses are designed with a gentle learning curve, placing a strong emphasis on hands-on experience and individualized instruction. Our dedicated team of instructors and teaching assistants ensure personalized guidance every step of the way.

Teaching Methodology:

Students work through tons of real-life examples using sample datasets donated by our mentors and corporate partners. We believe in a learn-by-building approach, and we employ instructors who are uncompromisingly passionate about your growth and education.