Is this you? As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.
Claim your profile
Articles by Nikolas Adaloglou
ICCV 2023 top papers, general trends, and personal picks
I was lucky and privileged enough to attend the ICCV 2023 conference in Paris. After collecting papers and notes I decided to share my notes along with my favourite ones. Here are the best papers picked out along with their key ideas. If you like my notes below, share them on social media! Towards understanding the connection between generative and discriminative learning Key idea: A very new trend that I am extremely excited about is the connection between generative and discriminative modeling.
Understanding Vision Transformers (ViTs): Hidden properties, insights, and robustness of their representations
× It is well-established that Vision Transformers (ViTs) can outperform convolutional neural networks (CNNs), such as ResNets in image recognition. But what are the factors that cause ViTs' superior performance? To answer this, we investigate the learned representations of pretrained models. In this article, we will explore various topics based on high-impact computer vision papers: The texture-shape cue conflict and the issues that come with supervised training on ImageNet.
How diffusion models work: the math from scratch
Diffusion models are a new class of state-of-the-art generative models that generate diverse high-resolution images. They have already attracted a lot of attention after OpenAI, Nvidia and Google managed to train large-scale models. Example architectures that are based on diffusion models are GLIDE, DALLE-2, Imagen, and the full open-source stable diffusion. But what is the main principle behind them? In this blog post, we will dig our way up from the basic principles.
Understanding Maximum Likelihood Estimation in Supervised Learning
Γ This article demystifies the ML learning modeling process under the prism of statistics. We will understand how our assumptions on the data enable us to create meaningful optimization problems. In fact, we will derive commonly used criteria such as cross-entropy in classification and mean square error in regression. Finally, I am trying to answer an interview question that I encountered: What would happen if we use MSE on binary classification?
Best AI and Deep learning books to read in 2022
So little time, so much to learn. Several books focus on deep learning have been written in the last few years. The competition is intense and it’s so hard to pick the best ones. We’ve certainly missed very good candidates but we believe these books are more than enough to fill your time dedicated to reading. We have probably never finished a single one of those books ourselves. Still, we occasionally visit specific chapters or sections.
Best deep CNN architectures and their principles: from AlexNet to EfficientNet
What a rapid progress in ~8.5 years of deep learning! Back in 2012, Alexnet scored 63.3% Top-1 accuracy on ImageNet. Now, we are over 90% with EfficientNet architectures and teacher-student training. If we plot the accuracy of all the reported works on Imagenet, we would get something like this: Source: Papers with Code - Imagenet Benchmark In this article, we will focus on the evolution of convolutional neural networks (CNN) architectures.
How Transformers work in deep learning and NLP: an intuitive introduction | AI Summer
The famous paper “Attention is all you need” in 2017 changed the way we were thinking about attention. With enough data, matrix multiplications, linear layers, and layer normalization we can perform state-of-the-art-machine-translation. Nonetheless, 2020 was definitely the year of transformers! From natural language now they are into computer vision tasks. How did we go from attention to self-attention? Why does the transformer work so damn well? What are the critical components for its success?
How Attention works in Deep Learning: understanding the attention mechanism in sequence models
I have always worked on computer vision applications. Honestly, transformers and attention-based methods were always the fancy things that I never spent the time to study. You know, maybe later and etc. Now they managed to reach state-of-the-art performance in ImageNet [3]. In NLP, transformers and attention have been utilized successfully in a plethora of tasks including reading comprehension, abstractive summarization, word completion, and others.
Self-supervised representation learning on videos
Nowadays, transfer learning from pretrained models on Imagenet is the ultimate standard in computer vision. Self-supervised learning dominates natural language processing, but this doesn’t mean that there are no significant use-cases for computer vision that it should be considered. There are indeed a lot of cool self-supervised tasks that one can devise when she/he is dealing with images, such as jigsaw puzzles [6], image colorization, image inpainting, or even unsupervised .
Show More
loading
Actions
Is this you?
As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.Get in touch with Nikolas
Contact Nikolas, search articles and posts on X, monitor coverage, and track replies from one place.
Learn more about Muck Rack