Scribd
Upload
2 views10 pages

Lecture_1

CS460: Deep Learning is a course that explores deep learning algorithms, their applications, and challenges, focusing on models like Artificial Neural Networks and Convolutional Neural Networks. The course includes written examinations, practical projects, and homework assignments for assessment. Key topics include the nature of learning, the distinction between machine learning and deep learning, and the factors that have enabled the advancement of deep learning technologies.

Uploaded by

Abdelrhman Adel
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
2 views10 pages

Lecture_1

CS460: Deep Learning is a course that explores deep learning algorithms, their applications, and challenges, focusing on models like Artificial Neural Networks and Convolutional Neural Networks. The course includes written examinations, practical projects, and homework assignments for assessment. Key topics include the nature of learning, the distinction between machine learning and deep learning, and the factors that have enabled the advancement of deep learning technologies.

Uploaded by

Abdelrhman Adel
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 10

Week 1: Introduction

CS460: Deep Learning


Course Description
 In this course, students will gain insight into the
Deep learning algorithms, how they work, their
strengths, challenges that lie ahead of them
and when to apply them.
 We will investigate various Deep Learning
models from the supervised and unsupervised
learning domain.
 We will examine various existing pipelines used
for handling real-world applications.
 The focus will be on Artificial Neural Networks
(ANN), Convolution Neural Networks (CNN), and
various generative models.
Books

 Ian Goodfellow and Yoshua Bengio


(2016), Deep Learning, MIT Press.
 Mohamed Elgendy (2020), Deep
Learning for Vision Systems,
Manning.
 Francois Chollet (2017), Deep
Learning with Python, Manning
Marks distribution

 7thweek: written examinations (30


marks)
 12th week: Practical Project (20
marks)
 Final: written exam (40 marks)
 Coursework: 2 homework
assignments
 Submission 6th and 13th week (10 marks)
Where are we?
What is learning?

 In general, learning is the


understanding and cognition of
abstract concepts.
 In a ML practical sense, it is the
process of building models for
automated data analysis.
 Determination of the parameters (&
hyperparameters) of the
mathematical function.
 Another word for it: Training
Machine Learning (ML) &
Deep Learning (DL)
 ML: is a set of mathematical
functions used to map the input to
the output. These functions can
extract non-redundant information or
patterns from the data, which
enables them to form a relationship
between the input and the output.
 In DL: there are more & more layers
of these mathematical functions
resulting in a complex mapping
How DL became a
possibility?
 Accelerated Computational power
 GPUs
 Availability of large datasets.
 To overcome overfitting
Why go deep?

 Increasedmathematical function
complexity
 Added abstractions of the input
 Automated feature extraction
Learning settings

 Supervised vs Non-supervised vs
Reinforcement learning modes
 Hybrid: Semi-supervised learning
mode
 Discriminative vs generative models

You might also like