Deep Learning for Computer Vision (Cohort 6)

As applied engineering just knows building models are not sufficient for production grade software, these roles focus on core principles, best practices, design patterns, and expertise with a framework and toolset, such as deploy models, and scale for your fast growing applications/services.
This 4 weeks immersive instructor-led course will teach everything you need to know to become a software engineer in computer vision and deep learning! You will learn:
  • Recognize problems can be solved with deep learning
  • Select the right technique for the problems.
  • Master deep learning algorithms, models and computer vision tech
  • Master the most popular tools like numpy, Keras, Tensorflow, and openCV
  • Master google cloud deep learning pipelines
  • This course is packed with practical exercises and code labs. not only will you learn theory, but also get hands-on practice building your own models, tuning models, and serving models

  • We meet twice a week at online classroom (powered by zoom)
  • Practical walkthroughs that present solutions to actual, real-world image classification problems and challenges
  • Hands-on tutorials (with lots of code) that not only show you the algorithms behind deep learning for computer vision but their implementations as well
  • A no-nonsense teaching style that is guaranteed to cut through all the cruft and help you master deep learning for image understanding and visual recognition
  • End to end deep learning pipeline from building models to deploy and serve models
    • Session 1: Dec 1, 5pm-7pm PST (US Pacific Time, GMT-8)
    • Session 2: Dec 3, 5pm-7pm PST
    • Session 3: Dec 8, 5pm-7pm PST
    • Session 4: Dec 10, 5pm-7pm PST
    • Session 5: Dec 15, 5pm-7pm PST
    • Session 6: Dec 17, 5pm-7pm PST
    • Session 7: Dec 21, 5pm-7pm PST (Move 12/24 due to christmas eve)
    • Session 8: Dec 22, 5pm-7pm PST

    • 4 weeks / 8 sessions / 16 hours
    • 8 lectures / 6 code labs / Capstone project
    • Live Sessions(Zoom), Real time interaction
    • Slack support during and after class
    • One-year access to course materials

    Check the content tab for full course outlines.

    Developers interested in Computer Vision and Deep Learning

  • Basic familiarity with python
  • Difficulty Level
    Est. time spend per week: 4 hours live class (required) + 4 hours homework (required) + 4 hours projects (bonus, optional).

    Full refund upon request before the first session ends (Dec 1st, 2020 7:00pm PST). 5% transaction fee is not refundable.

    If missed live sessions, you can watch recordings any time, along with interactive learning tools, slides, course notes
    Students have 1-year access to all course materials

  • Earn Certificate of Completion
  • Scholarship is available, contact us for details
  • Cohort 5: Oct 6~29, 2020
  • Cohort 4: Aug 4~20, 2020
  • Cohort 3: Feb 15~16, 2020
  • Cohort 2: Aug 22~23, 2019
  • Cohort 1: Jun 15~16, 2019
  • Module 1: Computer Vision Models
    • Deep Neural Networks
      • Input Layer
      • Deep Neural Networks (DNN)
      • Feed Forward
      • DNN Binary Classifier
      • DNN Multi-Class Classifier
      • DNN Multi-Label Multi-Class Classifier
      • Code Lab
    • Convolutional and ResNet Neural Networks
      • Convolutional Neural Networks
      • CNN Classifier
      • Basic CNN
      • VGG/li>
      • Residual Networks (ResNet)
      • ResNet50/li>
      • Code lab

    Module 2: Computer Vision Data Engineering
    • Training Foundation
      • Feed Forward and Backward Propagation
      • Dataset Splitting
      • Normalization
      • Validation & Overfitting
      • Convergence
      • Checkpointing & Earlystopping
      • Hyperparameters
      • Invariance
      • Raw (Disk) Datasets
      • Model Save/Restore
      • Code lab

    Module 3: Training Models 1
    • Procedural Design Pattern
      • Procedural Design Pattern
      • Stem Component
      • Learner Component
      • Task Component
      • Code lab
    • Wide Convolutional Neural Networks
      • Inception
      • ResNeXt
      • Wide Residual Network (WRN)
      • code lab

    Module 4: Training Models 2
    • Alternative Connectivity Patterns
      • Densely Connected CNN (DenseNet)
      • SE-Net
      • Xception
      • code lab
    • Mobile Convolutional Neural Networks
      • MobileNet
      • SqueezeNet
      • ShuffleNet
      • Quantization
      • code lab

    Module 5: AutoEncoders and Optimization
    • AutoEncoders
      • Deep Neural Network AutoEncoder
      • Convolutional AutoEncoder
      • Sparse AutoEncoder
      • Denoising AutoEncoder
      • Super Resolution
      • Pre-text Tasks
      • code lab
    • Hyperparameter Tuning
      • Weight Initialization
      • Warmup (Numerical Stability)
      • Hyperparameter Search
      • Learning Rate Scheduler
      • Regularization
      • Code lab

    Module 6: Transfer Learning
    • Transfer Learning
      • Tf.Keras Pre-Built Models
      • TF.Hub Pre-Built Models
      • Transfer Learning
      • code lab
    • Data Distributions
    • Dataset Curation

    Module 7: Data Pipeline
    • Data Formats & Storage
    • Data Feeding
    • Data Preprocessing
    • Data Augmentation
    • Code lab

    Module 8: Deployment in Production and Student Projects Presentation
    • Training Pipeline
    • Model Feeding
    • Training Schedulers
    • Model Evaluations
    • Serving
    • Student Projects Presentation
    Andrew Ferlitsch

    Andrew is a machine learning expert at Google. he educates software engineers in machine learning and artificial intelligence. He is the creator of and oversees the development of the open source project Gap, which is a ML data engineering framework for computer vision. Andrew was formerly a principal research scientist at Sharp Corporation, working on imaging, energy, solar, teleconferencing, digital signage, and autonomous vehicles.
    (197 Ratings)

    Student Feedback


    Hands-on examples and the teacher's experience. (Patricio from Class 20201006)

    Being able to interface with knowledgeable and patient person about the Deep Computer Vision technology. (Henok from Class 20201006)

    The subject area was interesting, but I felt the course dove too rapidly into the details of how to use tensorflow.keras. I would have appreciated more class time on theory and concepts, with exploring tensorflow more as self-guided labs. (Yossarian from Class 20201006)

    It was a great course. I really learned a lot. (BUKASA from Class 20200804)

    The depth and background of the instructor. He knows the ins and outs of Deep Learning for CV especially with TensorFLOW. (Charlie from Class 20200804)

    The in-depth look at the deep learning models, Code snippets explaining how-to and historical background. (Sarah from Class 20200804)

    Very passionate speaker, did a lot of explaining of the concepts with very understandable language. You could see he understands everything in such a way that he could explain it to a 5-year old. I would gladly attend another training led by him. Thumbs up. (Class 20200215)

    This was very good course, wish to have more sessions for more advanced topics and labs (Class 20200215)

    The instructor really good on explaining complex concepts with simple way to easily understand (Class 20200215)

    I really loved the pace and the fact that you explained everything intuitively. In addition, it was apparent that students really loved it. (Class 20190822)

    Good explaination and materials about Keras. Instructor's knowledge and experience (Class 20190822)

    good balance on tech concepts and hands-on code labs (Class 20190822)

    • Start Date: Dec 01, 17:00PST | Tue,Thu
    • Venue: Online (zoom)
    • Fee:
      $399 $249 USD
    • Max/Avail. Seats 25/11
    • Status: start soon
    • Course Preview:

    • Course Sample:

    • Any questions? Contact Us
    Enroll this course