As you might know, I regularly write on Medium covering topics such as Artificial Intelligence, Machine Learning, Deep Learning, Data Science, Data Visualization, TensorFlow, and other programming topics. Since the volume of my content reached a certain level, it got harder to see what I wrote about. So, I put together this guide to help you navigate around my content with ease.
I - Artificial Intelligence Essentials II - ML Programming Essentials III…
If you are reading this article, I am sure that we share similar interests and are/will be in similar industries. So let’s connect via Linkedin! Please do not hesitate to send a contact request! Orhan G. Yalçın - Linkedin
Before diving into this article, I just want to let you know that if you are into deep learning, I believe you should also check my other articles such as:
1 — Image Noise Reduction in 10 Minutes with Deep Convolutional Autoencoders where we learned to build autoencoders for image denoising;
Convolutional Neural Networks are a family of artificial neural network architectures that are specifically designed for computer vision and image processing tasks. It is a multi-layer neural network developed to analyze visual inputs and perform tasks like image segmentation, classification, denoising (with autoencoders), generation (with GANs), and object detection. On the other hand, in recent years, in addition to vision-related AI tasks, we started to see CNN implementations in other AI areas such as natural language processing (NLP).
Convolutional Neural Networks are the most important artificial neural network architecture today for almost any computer vision and image processing-related AI tasks. In this post, we will briefly visit the origins of CNNs from biological experiments of the 1950s until today’s complex pre-trained Computer Vision models.
In 1959, David Hubel and Torsten Wiesel discovered simple and complex cells. According to their study, for visual pattern recognition, we use two kinds of cells. A simple cell can recognize edges and bars of particular orientations at a particular part of the image, such as the image below:
Pandas is one of those libraries we always take for granted. When we work on our data projects, we always focus on building the best model using the latest and coolest deep learning framework like TensorFlow or PyTorch. Pandas is the library we inevitably used in the preprocessing every single time and forgot about it immediately. Well, the power of Pandas comes exactly from this: its convenience. In this post, we will cover one of the main data structures we see in the pandas library:
Let’s have a quick introduction
Pandas is a Python library that offers flexible and…
About two months ago, I wrote an article on Neural Style Transfer where we transfer van Gogh’s Unique Style to any photo with Magenta’s Arbitrary Image Stylization Network using TensorFlow. It showed how to quickly you can apply Neural Style Transfer without doing any fine-tuning.
I am sure you’ve come across dozens of newspaper articles talking about AI-generated text from news articles to poems, from novels to narrations. Wouldn’t it be cool if you can actually build a model that does that? Well, this is what we are gonna do in this post. We will build an RNN network that can generate text.
The research shows that one of the most effective artificial neural network types for Natural Language Processing tasks is Recurrent Neural Networks (RNNs). RNNs are widely used in NLP tasks such as machine translation, text generation, image captioning. In NLP tasks, we…
Data structures are fundamental constructs that are used to build programs. Each data structure has its own way of organizing data, which may work efficiently in particular use cases. With their own particular structures, data structures offer alternative solutions to data organization, management, storage, access, and modification tasks.
Regardless you are building a machine learning model or a mobile app; you must rely on data structures when working on a project. Therefore, your prospective employer will also want to make sure that you have a good grasp of data structures.
In this post, we will cover seven fundamental data structures…
You might have missed some of the latest developments in the AI world during your new year's holiday, but OpenAI released yet another revolutionary model on January 5, 2021: DALL·E. Named after the Spanish surrealist artist Salvador Dalí and Pixar’s science fiction bot WALL·E, DALL·E is creative as an artist and robust as a bot.
Based on the blog post's images, it seems that DALL·E has a good understanding of concepts like space, time, and logic.
This post will have a quick overview of what DALL·E is, what it can…
The field of deep learning has gained popularity with the rise of available processing power, storage space, and big data. Instead of using traditional machine learning models, AI engineers have been gradually switching to deep learning models. Where there is abundant data, deep learning models almost always outperform traditional machine learning models. This relationship can be visualized as follows: