Ders Adı Kodu Yarıyıl T+U Saat Kredi AKTS
Introductıon To Deep Learnıng ISE 469 7 3 + 0 3 5
Ön Koşul Dersleri
Önerilen Seçmeli Dersler
Dersin Dili Türkçe
Dersin Seviyesi Lisans
Dersin Türü Seçmeli
Dersin Koordinatörü Dr.Öğr.Üyesi BURCU ÇARKLI YAVUZ
Dersi Verenler Dr.Öğr.Üyesi BURCU ÇARKLI YAVUZ, Dr.Öğr.Üyesi SUNUSİ BALA ABDULLAHİ,
Dersin Yardımcıları
Dersin Kategorisi Diğer
Dersin Amacı

To teach mathematical fundamentals about deep learning, to use open source libraries related to deep learning, to develop deep learning applications.

Dersin İçeriği

Introduction to Artificial incelligence, machine learning and deep learning. Mathematical background. Gradient Descent algorithms, loss functions, backpropogation. Keras deep learning library,  tensor operations in Python.  Multi label classification, Regression. Data prepocessig, overfitting, weight regularization, dropout. 2D Convolution (conv2D) neural networks (convnets), pooling. Image data augmentation. Pretrained networks, fine tuning Visualizing convnet filters. Deep learning with text data. Emedding layers. Recurrent neural networks, LSTM and GRU layers. 1D convnets for sequence data.  Keras functional API,  Multi input multi output models. Generative deep learning.  Presentations about state of the art topics.

# Ders Öğrenme Çıktıları Öğretim Yöntemleri Ölçme Yöntemleri
1 Knows the basic topics about deep learning Lecture, Question-Answer, Discussion, Sightseeing, Observation,
2 Knows 1D and 2D convnet-convolution layers. Lecture, Question-Answer, Discussion, Sightseeing, Observation,
3 Uses open source libraries for deep learning Lecture, Question-Answer, Discussion, Sightseeing, Observation,
4 Knows text processing, Embedding Layer, Simple RNN, LTSM and GRU layers Lecture, Question-Answer, Discussion, Sightseeing, Observation,
Hafta Ders Konuları Ön Hazırlık
1 Introduction to Deep learning: Overview of Machine Learning, Deep Learning and Artificial Intelligence. Slides
2 Review of Mathematical Foundations: Linear Algebra, Probability, Information Theory. Slides
3 Gradient-based optimization: Overview of gradient descent algorithms, loss functions, and backpropagation. Slides
4 Overview of Machine Learning: Feedforward neural networks, Tree-based methods, etc. and ML-based packages. Slides
5 Basic concept of deep learning: Deep forward network and backpropagation, Regularization for deep learning, Keras deep learning library (Keras API). Slides
6 Deep learning training fundamentals: data preprocessing, preventing overfitting, weight regularization, dropout, pooling mechanisms, and optimization for training deep models. Slides
7 Convolutional Neural Network (CNN): 2-D Conv., CNN pooling and image classification. Slides
8 Sequence learning: 1-D CNN, RNN, LSTM, GRU, and Natural Language generation. Slides
9 Embedding representations: Embedding layers with text classification. Slides
10 Transfer Learning and Fine tuning. Slides
11 Autoencoders Slides
12 Advanced architectures: Attention, Attention CNN, Transformers,LLMs etc. Slides
13 Research presentations. Slides
14 Research presentations. Slides
Kaynaklar
Ders Notu

Weekly uploaded slides

Ders Kaynakları

Chollet, Francois. Deep learning with python. Manning Publications Co., 2017.

Goodfellow, Ian, et al. Deep learning. Vol. 1. Cambridge: MIT press, 2016.

Sıra Program Çıktıları Katkı Düzeyi
1 2 3 4 5
# Ders Öğrenme Çıktılarının Program Çıktılarına Katkısı
1 Knows the basic topics about deep learning
2 Knows 1D and 2D convnet-convolution layers.
3 Uses open source libraries for deep learning
4 Knows text processing, Embedding Layer, Simple RNN, LTSM and GRU layers
Değerlendirme Sistemi
Yarıyıl Çalışmaları Katkı Oranı
1. Ara Sınav 60
1. Ödev 10
2. Ödev 10
1. Proje / Tasarım 20
Toplam 100
1. Final 50
1. Yıl İçinin Başarıya 50
Toplam 100
AKTS - İş Yükü Etkinlik Sayı Süre (Saat) Toplam İş Yükü (Saat)
Course Duration (Including the exam week: 16x Total course hours) 16 3 48
Hours for off-the-classroom study (Pre-study, practice) 16 2 32
Mid-terms 1 10 10
Quiz 1 6 6
Performance Task (Application) 2 7 14
Final examination 1 15 15
Toplam İş Yükü 125
Toplam İş Yükü / 25 (Saat) 5
dersAKTSKredisi 5