MODULE OUTLINE
Deep Learning HDS401
Department of Analytics and Informatics
Lecturers: Ms L.K Nyandoro - Email: knyandoro@ceic.uz.ac.zw - Mobile: 0772331163
: Mr M. Panganai –Email: Mobile: mpanganai@ceic.uz.ac.zw –Mobile: 0772725181
LEARNING OBJECTIVES
By the end of the course, students will be able to:
1. Define deep learning and explain its key concepts.
2. Describe the different types of artificial neural networks and how they work.
3. Implement and train deep learning models using TensorFlow or PyTorch.
4. Apply deep learning algorithms to solve real-world data science problems, such as image
classification, object detection, natural language processing, and speech recognition.
5. Evaluate the performance of deep learning models and identify and address potential
problems, such as overfitting.
6. Discuss the ethical considerations involved in developing and deploying deep learning models.
7. Describe the architecture of a convolutional neural network.
8. Implement a convolutional neural network using TensorFlow or PyTorch.
9. Apply a convolutional neural network to solve a real-world image classification problem.
LEARNING OUTCOMES
Upon completion of this course, students will be able to:
1. Students will be able to define deep learning and explain its key concepts.
2. Students will be able to describe the different types of artificial neural networks and how they
work.
3. Students will be able to implement and train deep learning models using TensorFlow or
PyTorch.
4. Students will be able to apply deep learning algorithms to solve real-world data science
problems, such as image classification, object detection, natural language processing, and
speech recognition.
5. Students will be able to evaluate the performance of deep learning models and identify and
address potential problems, such as overfitting.
6. Students will be able to discuss the ethical considerations involved in developing and
deploying deep learning models.
Chapter 1: Introduction to deep learning
o What is deep learning?
o Why is deep learning important?
o Applications of deep learning
Chapter 2: Artificial neural networks
o What are artificial neural networks?
o How do artificial neural networks work?
o Different types of artificial neural networks
Chapter 3: Deep learning algorithms
o Convolutional neural networks (CNNs)
o Recurrent neural networks (RNNs)
o Long short-term memory (LSTM) networks
o Transformer networks
Chapter 4: Training and evaluating deep learning models
o Overfitting and how to avoid it
o Hyperparameter tuning
o Model selection
Chapter 5: Deep learning for data science applications
o Image classification
o Object detection
o Natural language processing
o Speech recognition
o Machine translation
o Recommendation systems
Chapter 6: Data preparation for deep learning
o TensorFlow and PyTorch - Two of the most popular deep learning frameworks
o Cleaning and preprocessing data
o Feature engineering
o Distributed deep learning
o Training and deploying deep learning models on large datasets
Chapter 7: Ethical considerations in deep learning
Evaluation Criteria
Assignments (groups/individual): 30%
Tests/ Quizzes: 20%
Final Exam: 50%
Textbooks and References:
1. Deep Learning by Ian Goodfellow, Yoshua Bengio, and Aaron Courville (2016)
2. Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow by Aurélien Géron
(2019)
3. Deep Learning with Python by François Chollet (2018)
4. Deep Learning for Coders with Fastai & PyTorch by Jeremy Howard, Sylvain Gugger, and
François Chollet (2020)
5. Generative Deep Learning by David J.C. MacKay (2018)
In addition to these textbooks, you can also find many online resources and tutorials on deep
learning. Some popular resources include:
Coursera
Udemy
YouTube
Google AI Blog
