fbpx

Convolutional Neural Network (CNN) for Quality Inspection

Learn how to automate the inspection process using Convolutional Neural Network (CNN)

  • Schedule

    22 – 24 February 2022

    18.30 – 21.30 (WIB)

  • Online-Interactive Learning

    Via Zoom

  • Investment

    Rp. 1.500.000

Course Summary

Casting is a manufacturing process in which liquid material is poured into a mold to solidify. Many types of defects or unwanted irregularities can occur during this process. The industry has its quality inspection department to remove defective products from the production line, but this is very time-consuming since it is carried out manually. Furthermore, there is a chance of misclassifying due to human error, causing rejection of the whole product order.

To solve these problems, we can use image data to create a machine learning model. One of the most popular and suitable methods to working with image datasets is the Convolutional Neural Network (CNN).

This 3-day online workshop is a beginner-friendly Deep Learning using Python. We will automate the inspection process by training top-view images of a casted submersible pump impeller using Convolutional Neural Network (CNN). One Instructor and two Teaching Assistants will help participants troubleshoot or help with any difficulties encountered.

NOTE: This workshop will be delivered in Bahasa Indonesia.

LEARNING OUTCOMES

Upon completion of this workshop, you will be able to:

  • Work with Python and pandas for data cleansing and manipulation processes.
  • Understand deep learning architecture
  • Work with Tensorflow for training data
  • Understand model reusability

Syllabus

  • Working with Conda Environment
  • Introduction to Python for data science
  • Data manipulation and processing with Python Pandas
  • Layer and neurons
  • Activation and cost function
  • Feedforward
  • Backpropagation
  • Convolution concept: kernel convolutional, strides, padding, and filter
  • Convolutional Neural Network Architecture
  • Load the data images and apply data augmentation techniques
  • Visualize the images
  • Training with validation: define the architecture, compile the model, model fitting, and evaluation
  • Testing on unseen images
  • Model logging and audit using Tensorboard

STUDENT TESTIMONIALS

This testimonial video is taken after our previous Online Data Science Series: Time Series Analysis for Business Forecasting.

LEARN FROM ANYWHERE

Our learning format is online-interactive, you will feel the interactive experience as if you were present in a physical classroom. You can access the class using your Zoom account on pre-defined dates.

  • LEARN AT YOUR OWN PACE

    Zoom recording, course Books (PDF & HTML files), the dataset for practice, reference notes, and working files are accessible through our Learning Management System account.

  • PROOF YOUR MASTERY

    Show current and prospective employers of your mastery in computer vision with a signed certificate of completion.

  • CONNECT WITH LIKE MINDED PEOPLE

    Be a part of our data-passionate community with 5000+ members and 1000+ alumni.

FOR ABSOLUTE BEGINNERS

Workshops in this series are tailored to casual programmers and non-programmers that are taking their first steps into data science. It assumes no prior knowledge or academic background, and attendees will be introduced to the beautiful art of writing R / Python code to produce data visualization and build machine learning models. The workshop has a gentle learning slope that is designed with non-technical professionals and academics in mind.

Yes, you can still attend the workshop as it is a beginner-friendly workshop.

Our system will send you an email containing a link and details to join a Google Classroom.

Online learning will be conducted via Zoom.us, Link to join the Zoom Class will be announced via Google Classroom.

Learning materials can be obtain via Google Classroom

Yes, you will receive a certificate of completion.

YOUR INSTRUCTOR

CNN

Dwi Gustin Nurdialit

A Data Science Instructor at Algoritma Data Science School, experience building data-intensive applications, tackling complex architecture and scalability issues across multiple industries. Proficient in predictive modeling, data processing, data mining algorithms, and scripting languages, including Python and R. Capable of creating, developing, and deploying various adaptive services to translate business and functional qualifications into tangible deliverables. She has more than 150 hours of teaching experience and has been involved in numerous consultative data science training and course production for our clients, to name a few:

  • Badan Tenaga Atom Nasional (BATAN)
  • Direktorat Jenderal Pajak (DJP)
  • Perusahaan Listrik Negara (PLN)
  • Telkom