• Live training

Workshop Solving Machine Learning Problems in TensorFlow/Keras​


This TensorFlow/Keras course enables further exploration of Machine Learning methods into the world of images. In order to easily grasp the concepts listed below, the student should already be familiar with Basic Machine Learning.

 

 

Esta formação é ministrada em Inglês.

Em parceria com a entidade acreditada:

 

Cursos relacionados

Pré-requisitos

Nice to have:

  • Basic Deep Learning
    • Neurons
    • Types of Layers
    • Networks
    • Loss Functions
    • Optimizers
    • Overfitting
    • Tensorflow
  • Basic Image Processing/Computer Vision
    • Encoding
    • Color Spaces
    • Convolutions
    • OpenCV/PIL

Programa

  • Introduction to Deep Learning in Image Processing
  • Basic Image Processing and Computer Vision
  • Supervised Neural Networks and Regularization
  • Convolutional Neural Networks
  • Common Convolutional Neural Networks Architectures
  • Reusing Convolutional Neural Networks
  • Real World Machine Learning
  • Explainable AI
  • Unsupervised Generative Models for Image Processing
  • Hands-on Lab:
  • Real World Machine Learning

 

Introduction to Deep Learning in Image Processing

  • Machine Learning and Deep Learning
  • Neural Network Anatomy
  • Types of Convolutions
  • Keras Workflow

 

Basic Image Processing and Computer Vision

  • Pixels and Images
  • Coordinate System
  • Channels
  • OpenCV
  • Channel Ordering
  • Blur and Sharpen kernels

Hands-on Lab:

  • Learn basic Image Processing using OpenCV
  • Learn to apply different filter kernels on images for blur generation or basic edge detection

 

Supervised Neural Networks and Regularization

  • Underfitting
  • Overfitting
  • Reducing the networks size
  • Weight Regularization: L1, L2, Elastic
  • Dropout
  • Batch Normalization

Hands-on Lab: Implement your first basic neural network, learn how to benchmark it and learn how to avoid overfitting on a Computer Vision classification task

 

Convolutional Neural Networks

  • Convolutional Layers
  • Depthwise Convolutions
  • Building Convolutional Neural Networks in Keras
  • 1×1 Convolutions
  • Data Augmentation

Hands-on Lab: Improve your previous neural network by adding Convolutional Layers, benchmark them and compare them with the Fully Connected ones

 

Common Convolutional Neural Networks Architectures

  • ImageNet
  • AlexNet
  • VGGNet
  • ResNet
  • MobileNet

Hands-on Lab: Learn how to use already state of the art models from the Keras Hub.

 

Reusing Convolutional Neural Networks

  • Object Localization
  • Object Segmentation
  • Reusing VGG
  • Fine-tuning

Real World Machine Learning

  • Tensorboard
  • Deploying Deep Learning Models
  • Choosing the algorithm

Learn how to fine parameter tune your already trained Convolutional Neural Network to fit your task

 

Explainable AI

  • Visualizing intermediate activations
  • Visualizing convnet
  • Visualizing heatmaps

 

Unsupervised Generative Models for Image Processing

  • Autoencoders for Images
  • Deblurring
  • Image generation

Hands-on Lab:

  • Generate a new image similar to the ones from the dataset by using a random seed
  • Face generation techniques

 

Real World Machine Learning

  • Tensorboard
  • Deploying Deep Learning Models
  • Choosing the algorithm

 

Workshop Solving Machine Learning Problems in TensorFlow/Keras​

Área

Dados

Como chegou até nós

Os seus dados pessoais são recolhidos em conformidade com o Regulamento Geral de Proteção de Dados (RGPD).

Consente que os seus dados sejam utilizados, nos termos da nossa Politica de Privacidade, para o contacto/envio de:

Ações de informação, de marketing de produtos e serviços, como campanhas e eventos?

Para mais informações, consulte a Política de Privacidade do Grupo Rumos.
pode retirar o seu consentimento a qualquer momento através do botão Cancelar subscrição ou Unsubscribe que estão presentes em cada comunicação enviada, bem como exercer os direitos descritos na politica de privacidade