CS计算机代考程序代写 python deep learning Keras AI algorithm Deep Learning – COSC2779 – Introduction to Deep Learning

Deep Learning – COSC2779 – Introduction to Deep Learning

Deep Learning – COSC2779
Introduction to Deep Learning

Dr. Ruwan Tennakoon

July 19, 2021

Lecture 1 (Part 1) Deep Learning – COSC2779 July 19, 2021 1 / 16

Outline

1 Introduction: Teaching Team
2 Course Overview
3 Introduction to Deep Learning
4 Review of Machine Learning Fundamentals

Lecture 1 (Part 1) Deep Learning – COSC2779 July 19, 2021 2 / 16

Dr Ruwan Tennakoon (Lecturer – Artificial Intelligence)

Ruwans research interests:
Computer Vision & Machine Learning
Medical Image Analysis
Statistical Signal Processing

If you are interested in my research: Google
Scholar Profile

Official consultation hours: Wednesday’s 3.00pm – 4.00pm (MS Teams).

Lecture 1 (Part 1) Deep Learning – COSC2779 July 19, 2021 3 / 16

https://scholar.google.com.au/citations?user=jJLCih0AAAAJ&hl=en
https://scholar.google.com.au/citations?user=jJLCih0AAAAJ&hl=en

Dr Iman Abbasnejad (Senior Research Fellow)

Iman’s research interests:
Computer Vision & Machine Learning
Generative Adversarial Networks (GAN)

If you are interested in Imans’s research: Google
Scholar Profile

Lecture 1 (Part 1) Deep Learning – COSC2779 July 19, 2021 4 / 16

https://scholar.google.com/citations?user=-tENCAUAAAAJ&hl=en
https://scholar.google.com/citations?user=-tENCAUAAAAJ&hl=en

Objectives of Our Course

Learn about Deep learning (DL) conceptually and practically.
Different problem types of DL and sample of approaches.
Learn about the typical process of developing deep Neural Networks.
Apply these to solving real world prediction and exploratory tasks.

Focus on:
Analysis of what the algorithms are doing.
Analysis of the data set and results
Learning an initial set of tools, the key DL techniques.
Terminology and concepts so can learn other DL approaches not covered
in course.

The complete set of learning objectives are in the Course guide

Lecture 1 (Part 1) Deep Learning – COSC2779 July 19, 2021 5 / 16

http://www1.rmit.edu.au/courses/053577

Course Information

Official Prerequisite:
Computational Machine Learning –
COSC2793

Desirable:
Knowledge of Python
Calculus (gradients)
Linear Algebra
Optimisation
Probability and Statistics
Algorithms

Machine Learning: Statistics, Algorithm &
complexity theory, Optimization.

See Canvas Week 1 Optional readings for some reversion materials.

Lecture 1 (Part 1) Deep Learning – COSC2779 July 19, 2021 6 / 16

Course Structure

Week 1 Introduction Deep Learning
Week 2 Deep Feed Forward Networks
Week 3 Neural Network Optimization
Week 4 Convolutional Neural Networks
Week 5 Vision Application & CNN Architectures
Week 6 Practical methodology/Hyper parameter tuning
Week 7 Modelling Sequential (Time Series) Data
Week 8 Time Series Applications
Week 9 Unsupervised Learning/Generative Models
Week 10 Representation Learning/Self Supervised Learning
Week 11 Neural Network Model Interpretation/Explainable AI (XAI)
Week 12 Review

CNN

Time Series

Advanced Topics

Lecture 1 (Part 1) Deep Learning – COSC2779 July 19, 2021 7 / 16

Course Information

Delivery mode: Blended Delivery (Online + on-campus)
Classroom and Hours:

Lecture Videos: Pre-recorded and will be made available via course MS
Stream channel.
Lectures (Lectorial): Monday 6:30 – 8:30pm (MS Teams). Will also
contain information that is not covered in the pre-recorded videos.
Lab/Tute: Wednesday 6.30 – 8.30 pm (On-Campus/On-line)

The Lectorials & the Consultation sessions will be conducted via MSTeam
– “COSC2779 2150”. Please follow the instructions on canvas page Week
0: Getting started to join the team.
Canvas: Everything (slides/homeworks/projects/discussion board etc.)

Lecture 1 (Part 1) Deep Learning – COSC2779 July 19, 2021 8 / 16

https://rmit.instructure.com/courses/79678/pages/week-0-getting-started?module_item_id=3360689
https://rmit.instructure.com/courses/79678/pages/week-0-getting-started?module_item_id=3360689

Course Structure

Lecture 1 (Part 1) Deep Learning – COSC2779 July 19, 2021 9 / 16

Online Delivery

Lectures: Synchronous + Asynchronous
Each week a set of pre-recorded videos will be a available prior to the lecture (Monday).
Please make sure that you go through them before joining the lecture.
There will be a MS teams session during the timetable slot.
MS teams Lecture will cover summary of pre-recorded videos, additional materiel and
Q&A.

Lab/Tutorials: On-Campus + on-line.
Each week lab exercises and tutorial questions will be made available prior to class.
Please make sure that you go through them before joining and be prepared to discuss
the ideas.
Labs will be a good place to ask questions on assignments.

Self Study You are also expected to spend a significant amount of time in private
study, working through the course as presented in classes and learning materials and
gaining practice at solving conceptual and technical problems.
Office hours (consultation): Via MS Teams – See canvas for details.

Lecture 1 (Part 1) Deep Learning – COSC2779 July 19, 2021 10 / 16

Course Workload and Assignments
Workload (every week): > 10hrs:

Four Contact hours: Lecture 2hrs, Lab/Tutorial 2hr
At least six Self study hours (include pre recorded videos)

Assignments:
Introduction to DL (30%) – Due Monday Week 7
DL Project (50%) – Due Friday Week 11
Virtual Presentation & Interview (20%) Will be scheduled in week 14.

Late penalty for assignments

Standard CS, -10% each day.
Set last day for submission.
Special Consideration may result in equivalent assessment, not extensions.

Lecture 1 (Part 1) Deep Learning – COSC2779 July 19, 2021 11 / 16

Text and Reference Books

Primary reference:
Ian Goodfellow, Yoshua Bengio, Aaron Courville, Deep Learning , MIT
Press, 2016, http://www.deeplearningbook.org.

Other references:
TensorFlow Tutorials
Oswald Campesato, TensorFlow 2.0 pocket primer, 2020. Library Link.
Tom Mitchell, Machine Learning , McGraw Hill, 1997.
Neural Networks and Deep Learning by Michael Nielsen Link

Additional Reading material (references) specific to each week will be made
available via the relevant canvas module.

Lecture 1 (Part 1) Deep Learning – COSC2779 July 19, 2021 12 / 16

http://www.deeplearningbook.org
https://www.tensorflow.org/tutorials
https://primo-direct-apac.hosted.exlibrisgroup.com/permalink/f/1d27kpc/RMIT_ALMA51224807240001341
http://neuralnetworksanddeeplearning.com/index.html

Expectations

Us → You
This is an elective (for most of you). Hence we do expect you to work
hard and be highly motivated.
Please attend online classes.
Interact while in class! Be curious, ask questions.
We try to be fair as possible and allow you opportunities to ask us about
assessment marks, but please do not haggle about them.
Please don’t cheat!

You → Us
We will strive to be prompt in replying to your requests.
We provide support and help for you to achieve the best learning
outcomes as you can.

Lecture 1 (Part 1) Deep Learning – COSC2779 July 19, 2021 13 / 16

Communication Channels

Us → You
Announcements are made regularly on Canvas.
Emails will be sent out on a need basis.
Lecture announcements.

You → Us
Consultation hours, email, before/after class, during labs.
Official consultation hours: Wednesday’s 2.00pm – 3.00pm (MS Teams).

Many → Many
Discussion Board on Canvas. Please don’t hesitate to reply to queries on
discussion boards.

Lecture 1 (Part 1) Deep Learning – COSC2779 July 19, 2021 14 / 16

Tools and Infrastructure

The programming language used for the course will be Python. Deep learning
models will be implemented with Tensorflow 2.0 + Keras.

Infrastructure:
Google Colab

More details on the above platforms and information to get started is provided
in week 1 lab exercises (self-study).
Tensorflow tutorials https://www.tensorflow.org/tutorials

Lecture 1 (Part 1) Deep Learning – COSC2779 July 19, 2021 15 / 16

https://www.tensorflow.org/tutorials

Academic Integrity

Academic Integrity

Please see:
https://www.rmit.edu.au/students/student-essentials/
rights-and-responsibilities/academic-integrity

You are encouraged to form groups to solve problems; however,
when writing or programming, write in your own words or code,
and provide your own solutions.
This is not about penalising or yielding the stick, but you’ve made
a conscious act to enroll in this course (thank-you), and we want
you to:

Learn by trying things, making mistakes
Fair for everyone
Quality control of your degree

Lecture 1 (Part 1) Deep Learning – COSC2779 July 19, 2021 16 / 16

https://www.rmit.edu.au/students/student-essentials/rights-and-responsibilities/academic-integrity
https://www.rmit.edu.au/students/student-essentials/rights-and-responsibilities/academic-integrity

Introduction: Teaching Team
Course Overview
Introduction to Deep Learning
Review of Machine Learning Fundamentals