Hotline : 0811-9720-2000, CODEVA OFFERS OFFLINE AND ONLINE COURSES Office : 021 3002 0942 info@codeva.co.id
Select Page

Deep Learning (with TensorFlow 2, Keras and PyTorch)

Fill Out The Form For FREE Classes And To View Codeva Program Packages

Intermediate

Deep Learning (with TensorFlow 2,

Keras and PyTorch)

This course is an introduction to artificial neural networks that brings high-level theory to life with interactive labs featuring TensorFlow, Keras, and PyTorch — the leading Deep Learning libraries. Essential theory will be covered in a manner that provides students with a complete intuitive understanding of Deep Learning’s underlying foundations. Paired with hands-on code run-throughs in Jupyter notebooks as well as strategic advice for overcoming common pitfalls, this foundational knowledge will empower individuals with no previous understanding of neural networks to build production-ready Deep Learning applications across all of the contemporary families, including:

  • Convolutional Networks for machine vision
  • Long Short-Term Memory Recurrent Nets for natural language processing and time series analysis
  • Generative Adversarial Networks for producing jaw-dropping synthetic data
  • Reinforcement Learning for complex sequential decision-making

Course Overview

Facilitated by the confluence of inexpensive computing power, unprecedentedly large data sets, and clever theoretical advances, Deep Learning algorithms are driving the contemporary revolution in Artificial Intelligence. Deep Learning has emerged as uniquely influential across a broad range of applications, including classification (e.g., visual recognition, sentiment analysis), prediction (e.g., stock markets, health outcomes), generation (e.g., creating works of art, composing music), and sequential decision-making (e.g., games,robotics). In the past few years, Deep Neural Networks have made their way into countless everyday applications, including Tesla’s Autopilot, Amazon’s Alexa, and Google’s suggested email replies. Indeed, Deep Learning algorithms have exceeded human performance on previously intractable computational problems like language translation, object detection, and the game of Go.

This course is an introduction to artificial neural networks that brings high-level theory to life with interactive labs featuring TensorFlow 2, Keras, and PyTorch — the three principal Deep Learning libraries. Essential theory will be covered in a manner that provides students with a complete intuitive understanding of Deep Learning’s underlying foundations. Paired with hands-on code run-throughs in Jupyter notebooks as well as strategic advice for overcoming common pitfalls, this foundational knowledge will empower individuals with no previous understanding of neural networks to build production-ready Deep Learning applications across all of the contemporary families, including:

  • Convolutional Networks for machine vision
  • Long Short-Term Memory Recurrent Nets for natural language processing and time series analysis
  • Generative Adversarial Networks for producing jaw-dropping synthetic data
  • Deep Reinforcement Learning for complex sequential decision-making

Prerequisites

It would be challenging to follow along through the code demos and exercises without some experience in object-oriented programming, ideally Python (introductory course here). Students with experience in other languages (e.g., R) have, however, been very successful.

Certificate

Certificates are awarded at the end of the program at the satisfactory completion of the course. Students are evaluated on a pass/fail basis for their performance on the required homework and final project (where applicable). Students who complete 80% of the homework and attend a minimum of 85% of all classes are eligible for the certificate of completion.

Syllabus

Unit 1: The Unreasonable Effectiveness of Deep Learning

  • An Introduction to Neural Networks and Deep Learning
  • Interactive Visualization of an Artificial Neural Network
  • Hardware Options for Deep Learning, including How to Build a Deep Learning Server
  • Running Jupyter Notebooks within a Docker Container
  • The Families of Deep Neural Nets and their Applications
  • A Shallow TensorFlow 2 Neural Network with Keras Layers

Unit 2: How Deep Learning Works

  • Essential Theory I: Neural Units
  • Interactive Visualization of Neural Units
  • Essential Theory II: Cost Functions, Gradient Descent, and Backpropagation
  • Interactive Visualization of Neural Networks
  • An Intermediate Neural Network
  • Data Sets for Deep Learning
  • Your Deep Learning Project: Ideating

Unit 3: Building and Training a Deep Learning Network

  • Review Content and Take-Home Exercises
  • Essential Theory III: Weight Initialization and Mini-Batches
  • Essential Theory IV: Unstable Gradients and Avoiding Overfitting
  • A Deep TensorFlow 2 Neural Network with Keras Layers
  • TensorBoard and the Interpretation of Model Outputs

Unit 4: Machine Vision

  • Introduction to Convolutional Neural Networks for Visual Recognition
  • Classic ConvNet Architectures: LeNet-5 and AlexNet
  • Object Detection
  • Image Segmentation
  • Transfer Learning
  • Your Deep Learning Project: Formulating

Unit 5: Natural Language Processing

  • Reviewing Content and Take-Home Exercises
  • Word Vectors: word2vec and Vector-Space Embedding
  • Recurrent Neural Networks
  • Long Short-Term Memory Units
  • Gated Recurrent Units
  • Classifying Documents: Sentiment Analysis

Unit 6: Time Series Analysis

  • Autoencoders: Encoder-Decoder Structures
  • Sequence-to-Sequence Models and Attention
  • Financial Forecasting
  • Hyperparameter Tuning
  • Non-Sequential Models
  • Your Deep Learning Project: Assessing

Unit 7: Advanced TensorFlow

  • Introducing TensorFlow Graphs
  • Representing Neurons as TensorFlow Graphs
  • Optimizing TensorFlow Graphs
  • Deep Learning with TensorFlow 1.x
  • Deep Learning with TensorFlow 2.x

Unit 8: PyTorch

  • Comparison of the Leading Deep Learning Libraries
  • Autodifferentiation
  • Sequential Deep Learning Models in PyTorch
  • Forward Propagation and Optimization in PyTorch
  • Model Validation in PyTorch
  • Your Deep Learning Project: Improving

Unit 9: Generative Adversarial Networks

  • GAN Applications
  • Essential GAN Theory
  • Simulating Artistic Creativity with a GAN
  • Resources for Deep Learning Self-Study

Unit 10: Reinforcement Learning

  • Applications of Reinforcement Learning
  • Reinforcement Learning Environments: OpenAI Gym
  • Essential Reinforcement Learning Theory
  • Deep Q-Learning Networks
  • Policy Gradients and the Actor-Critic Algorithm
  • Jeanne Calment and Your Role in the AI Revolution
  • Your Deep Learning Project: Presentation
×