Deep Learning for CV and NLP - Seattle

Description
Content
Speaker
COURSE OBJECTIVES:
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 three-day immersive instructor-led training will teach everything you need to know to become a software engineer in deep learning, computer vision and NLP! You will learn:
  • Recognize problems can be solved with deep learning and Select right technique for problems
  • Select the right technique for the problems.
  • Master deep learning algorithms, models and computer vision and NLP tech
  • Master the most popular tools like numpy, Keras, Tensorflow, and openCV
  • Master google cloud machine learning pipelines
  • Get started on NLP and NLP pipeline
  • Use NLP to solve real world problem
  • This training 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

    COURSE SCHEDULE:
    • Oct 3rd, 9am-4:00pm PT
    • Oct 4th, 9am-4:00pm PT
    • Oct 5th, 9am-4:00pm PT

    COURSE INCLUDE:
    • Practical walkthroughs that present solutions to actual, real-world deep learning 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, visual recognition, and NLP
    • End to end machine learning pipeline from building models to deploy and serve models
    • Lunch, coffee breaks, and happy hour

    COURSE CONTENT:
    Check the content tab for full course outlines.

    WHO SHOULD LEARN:
    Developers interested in Deep Learning, computer vision, and NLP

    PREREQUISITE:
    Python

    PAST SESSIONS
  • Seattle: 6/15-16, 2019
  • Portland: 8/6-7, 2019
  • San Francisco: 8/22-23, 2019
  • STUDENT FEEDBACKS
  • Overall score: 4.5 / 5
  • Score: 5 (58%); 4 (42%)
  • REVIEWS
  • "Personally I really loved the pace and the fact that you explained everything intuitively. In addition, it was apparent that students really loved it. " - UCLA Professor/CS 168
  • "good balance on tech concepts and hands-on code labs"
  • "The instructor really good on explaining complex concepts with simple way to easily understand"
  • Pictures of Previous Courses

    Day 1 (9am -4:00pm)
    Module 1: Computer Vision Models
    • Neural Networks
      • Activation, loss function
      • classifier
      • Flattening, overfitting, dropout
      • code lab with Keras
    • Convolutional Neural Networks
      • resize, feature detection
      • filters, strides, pooling
      • VGG, ResNet
      • Batch normalization
      • code lab with Keras
    • Wide Convolutional Neural Networks
      • inception, ResNeXt
      • code lab
    • Advanced CNNs
      • pre-stems, DenseNet, MobileNet
      • code lab
    Module 2: Computer Vision Data Engineering
    • Data Collection & Assembly
      • best practice
      • unbalanced data
      • insufficient variance
      • dataset layout
    • Data Engineering
      • PIL
      • Normalization and Standardization
      • label encoding
      • data splitting
      • openCV
    • Data Augmentation
      • under-fitting
      • perspective
      • flipping
      • rotation
      • code lab with Keras
    • Data Curation
      • population distribution
      • sampling distribution
      • code lab with Keras
    Day 2 (9am -4:00pm)
    Module 3: Training Models
    • Training Preparation
      • splitting
      • shuffling
      • stratification
      • code lab
    • Hyperparameter Tuning
      • Epochs and Steps
      • Batch size
      • learning rate
      • optimizer
      • feeding
      • code lab
    • Training
      • pre-training
      • weight initialization
      • Grid Search
      • Gradient Descent
    • Pre-Built Models & Transfer Learning
    Module 4: Deployment and Production
    • Intro to TensorFlow 2.0, tf.Keras, tools (Colab, TensorBoard)
    • Deploy models with TensorFlow serving
    • Model training and deployment in the browser with TensorFlow JS
    • On-device ML: train a model from scratch, convert to TFLite and deploy to mobile and IoT
    • Demo of TFLite models on microcontroller and Coral Edge TPU
    Day 3 (9am -4:00pm)
    Module 5: Overview of NLP and Deep Learning
    • Vector representations of Words: word2vec
    • Recurrent neural networks
    • LSTM&GRU
    • BERT
    Module 6: NLP Pipeline
    • Data preprocessing
    • Text embedding
    • Text Classification
    Module 7: Code Labs
    • Text Classification
    • Sentiment analysis
    Andrew, Zhen, Lingling

    Andrew Ferlitsch
    Machine learning engineer 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.
    Zhen Li
    Senior data scientist and AI lead at Microsoft. She has led initiatives to build various big data machine learning systems and helped to build the Azure Data Center Al Team.
    Lingling Zheng
    Senior data scientist at the Microsoft AI team. She is leading the machine learning effort to optimize data center critical environment operations. Previously at Amazon, she has led several initiatives to implement new algorithms for fraud detection
    • Start Date: Oct 03, 09:00PST | Thu~Sat
    • Venue: Seattle
    • Fee:
      $899 $449
    • Max/Avail. Seats 30/25
    • Status: start soon
    • Preview this course:
    • Help? Send Question
    Enroll This Course