inzvaDLSG

Introduction

The inzva Deep Learning Study Group (DLSG) serves as an essential guide for anyone looking to get started in the deep learning field. It not only offers a comprehensive introduction but also forms the backbone of our most fundamental study group, making it a critical resource for both beginners and those looking to deepen their knowledge. We extend our heartfelt thanks to all the contributors and volunteers of our community who have dedicated their time and effort to create and compile these invaluable resources. Their hard work has made this project possible, ensuring that the materials are accessible and beneficial to a wide range of learners. Every decision, from the content selection to the structure, has been made with great care and consideration.

This repository is not just a static collection of information but a living document that will be regularly updated to stay in line with the fast-paced developments in artificial intelligence. We hope this guide will serve as a cornerstone for anyone who is passionate about deep learning, inspiring further exploration.

Syllabus and Materials

inzvaDLSG-V2.0 (2026)

Weeks	Course Name	Topic	Bundle	Slide	Notebooks	Recommended Links
inzva Deep Learning Study Group
w1	Introduction to Neural Networks and Deep Learning	Introduction to Neural Networks	w1.1 w1.2	w1	pytorch_intro fmnist_test fmnist_train xor_linear_vs_mlp	[v1] [v2] [v3] [v4] [v5]
w2		Hyperparameter Tuning and Regularization	w2		exc
w3		Debugging & Optimization Algorithms
w4	Neural Network Architectures and Common Tasks in Deep Learning	CNN with Common Tasks: Image Classification, Object Detection, Image Segmentation
w5
w6		Transformers with Common Tasks: Neural Machine Translation, Image Classification
w7
w8		GNNs
w9	Trend Topics in Deep Learning: Generative Models and LLM's	Generative Models
w10		Introduction to Large Language Models (LLMs)
w11		Deep Learning at Scale: Tools & Ops

inzvaDLSG-V1.0 (2024)

Weeks	Course Name	Topic	Bundle	Slide	Notebooks	Recommended Links
inzva Deep Learning Study Group
w1	Introduction to inzva DLSG	Introduction to the Course	intro_nns	w1_s	pytorchintro fcn_exp1.1 fcn_exp1.2
		Introduction to Neural Networks				[v1] [v2] [v3] [v4] [t1]
w2	Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization	Hyperparameter Tuning and Regularization Methods	handbook	w2_s	exc soln
w3		Optimization Algorithms	optimization_algos	w3_s	visual_exp	[1]
w4	Neural Network Architectures and Common Tasks in Deep Learning	Convolutional Neural Networks with Common Tasks: Image Classification, Object Detection, Image Segmentation	conv_nns	w4_s	resnet_exp	[v1] [v2] [v3] [v4]
w5				**	seg_n_det_exp
w6		Recurrent Neural Networks with Common Tasks: Natural Language Processing	nlp_handbook	w6_s
w7				**	charlm_exp embeddings_exp emotion_exp
w8		Transformers with Common Tasks: Machine Translation, Image Classification	transformers	w8_s		[t1] [v1] [v2] [v3] [v4] [v5]
w9				**	vit_exp nmt_exp	[t1]
w10	Trend Topics in Deep Learning	Generative Models (VAEs, Diffusion Models)	intro_genai	w10_s	sdiffusion_exp	[v1]
w11		Introduction to Large Language Models (LLMs)	intro_llms	**	bert_exp t5_exp llama_exp

**: In the lecture, instead of a presentation, we either used bundles or had a practical session.

You can refer this abbreviations while checking the table:

• exp → example
• exc → exercise
• soln → solution
• seg → segmentation
• det → detection
• n → and
• s → presentation
• vX → Xth video (e.g., v1 stands for the first video related to the subject of the week)
• tX → Xth text (e.g., t1 stands for the first text related to the subject of the week)

Further Readings

• Alice’s Adventures in a differentiable wonderland
• Understanding Deep Learning
• Goodfellow's Deep Learning

Acknowledgements

Our beloved contributors:

• Berfin Duman
• Bike Sönmez
• Deniz Berkin Kahya
• Emir Erman Faruk
• Gürkan Soykan
• İrem Gülçin Zırhlıoğlu
• Melih Darcan
• Sarper Yurtseven
• Simge Şengül
• Şafak Bilici
• Şilan Fidan Vural
• Tarık Can Özden

A huge thank you to everyone who spent their time and energy into making the inzva Deep Learning Study Group a reality! Whether you were creating notebooks, prepare presentations, or creating our bundles your efforts have made this journey so much more impactful for everyone involved. We're so grateful to have such an amazing, supportive community making all of this possible. Thank you for being part of this journey and helping it grow!

inzva AI Team