Deep Learning Demystified: Foundations for Non-Computer Scientist

# Deep Learning Demystified: Foundations for Non-Computer Scientist

# Course Description

"Deep Learning Demystified: Foundations for Non-Computer Scientists" is an accessible and comprehensive course designed to introduce individuals from diverse backgrounds to the fundamental concepts of deep learning. Through clear explanations and real-world examples, participants will gain a solid understanding of key components of deep learning. By the end of the course, students will be equipped with the knowledge and confidence to engage with and apply deep learning techniques in various fields, regardless of their technical background.

# Objectives

  • Utilise the Tensorflow Keras framework to execute standard deep learning workflows.
  • Explore diverse data, training parameters, network architectures, and other methodologies to enhance performance and functionality.
  • Transition your trained neural networks into deployment to tackle practical challenges effectively.

# Pre-requisites

  • Basic knowledge of the Python programming language.

# Schedule

  • Day one
    • 13:00-14:10 | 01: Introduction to Deep Learning
    • 14:10-14:25 | Break
    • 14:25-15:35 | 02: Neural Networks
    • 15:35-15:50 | Break
    • 15:50-17:00 | 03: Classification and Convolutional Neural Networks
  • Day two
    • 13:00-14:30 | 04: Refining the model
    • 14:30-14:45 | Break
    • 14:45-15:30 | 05: Deployment & Transfer Learning
    • 15:30-16:00 | 06: DL in other fields
    • 16:00-16:15 | Break
    • 16:15-17:00 | 07: Final Exercise & Wrap-up

# Host Listings

# Overview

Python Colab notebook

# 01: Introduction to Deep Learning

# Lab 01: Introduction to Tensorflow Keras

Python Colab notebook

# 02: Neural networks

# Lab 02: Classifying images of clothing

Python Colab notebook

# 03: Classification and Convolutional Neural Networks

# Lab 03: Image classification with CNNs

Python Colab notebook

# 04: Refining the model

# Lab 04: Dogs & Cats with data augmentation

# 4a Without Data augmentation

Python Colab notebook

# 4b With Data augmentation

Python Colab notebook

# 05: Deployment & Transfer Learning

# Lab 05: Saving and Loading models

Python Colab notebook

# Lab 06: Tensorflow hub and Transfer learning

Python Colab notebook

# 06: DL in other fields

# Lab 07: Final exercise, flowers with data augmentation

Python Colab notebook

# Feedback

Please use the following form to provide feedback: https://forms.gle/UYgxhZyUwNopWRGf9 (opens new window)

# Extra Lab 01: Text classification with RNN

Python Colab notebook

# Extra Lab 02: Handwritten digits generation with DCGAN

Python Colab notebook