Demystifying Object Detection — I was first introduced to object detection through the Tensorflow Object Detection API. It was simple to use. I passed in an image of a beach and in return, the API painted boxes over the objects it recognized. It seemed magical. I became curious and wanted to dissect the API…

Generative adversarial networks or GANs for short are an unsupervised learning task where the generator model learns to discover patterns in the input data in such a way that the model can be used to generate new samples of the training data. The main idea of GAN is adversarial training…

What is the mathematical foundation of generative adversarial networks? — Generative Adversarial Networks or GANs have been a revolution in deep learning over the last decade. Since the first version of GAN that was released in 2014 by Ian Goodfellow et al., there have been numerous variants of GAN with some mind-blowing applications. In this article we shall try to…

Why does minimizing the norms induce regularization? — If you’ve taken an introductory Machine Learning class, you’ve certainly come across the issue of overfitting and been introduced to the concept of regularization and norm. I often see this being discussed purely by looking at the formulas, so I figured I’d try to give a better insight into why…

Learn a fundamental, yet often ‘hidden,’ concept of deep learning — What is Latent Space? If I have to describe latent space in one sentence, it simply means a representation of compressed data. Imagine a large dataset of handwritten digits (0–9) like the one shown above. Handwritten images of the same number (i.e. images that are 3’s) are the most similar to each other compared…

U-Net has become the go-to method for image segmentation. But how did it come to be? — Table of content 1. The task at hand 2. Encoder-Decoder 3. Skip connections 4. Implementation details a. Loss function b. Up-sampling methods c. To pad or not to pad? 5. U-Net in action The task at hand U-Net is developed for the task of semantic segmentation. When a neural network is fed images as…

Using Unsupervised Deep Learning to Generate Handwritten Digits with Deep Convolutional GANs using TensorFlow and the MNIST Dataset, in collaboration with VIZIO AI — Machines are generating perfect images these days and it’s becoming more and more difficult to distinguish the machine-generated images from the originals. 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…

Understanding the Generative Adversarial Network Generative Adversarial Network which is popularly known as GANs is a deep learning, unsupervised machine learning technique which is proposed in year 2014 through this research paper. The main blocks of this architecture are ; Generator : This block tries to generates the images which…

An article on a Deep Learning Architecture Inspired By An Internet Meme — and its technical information and details. — Introduction Back in 2014, researchers at Google (and other research institutions) published a paper that introduced a novel deep learning convolutional neural network architecture that was, at the time, the largest and most efficient deep neural network architecture. The novel architecture was an Inception Network, and a variant of this Network…

In this article, I will try to give a fairly simple and understandable explanation of one really fascinating type of neural network. Introduced by Cho, et al. in 2014, GRU (Gated Recurrent Unit) aims to solve the vanishing gradient problem which comes with a standard recurrent neural network. GRU can…

Comparable Performance With LSTM, Faster Convergence than Vanilla RNN — In this story, Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling, (GRU), by Université de Montréal, is briefly reviewed. This is a paper from Prof. Bengio’s group. In this paper: GRU is introduced with performance comparable with LSTM. This is a paper in 2014 NeurIPS with over 7800…

Table of Contents ∘ ⭐️ U-Net Recap ∘ ⭐️ UNet++ Innovations ∘ ⭐️ Loss function ∘ ⭐️ Performance · Citations In this article, we are going to introduce you to UNet++, essentially an upgraded version of U-Net. This article is designed to help you understand it intuitively and thoroughly with minimum time possible…

The Neural Network used by Open AI and DeepMind — If you liked this post and want to learn how machine learning algorithms work, how did they arise, and where are they going, I recommend the following: Making Things Think: How AI and Deep Learning Power the Products We Use - Holloway It is the obvious which is so difficult to see most of the time. People say 'It's as plain as the nose on your face.'…www.holloway.com

In their 2015 publication “Deep Residual Learning for Image Recognition,” Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun created a particular kind of neural network known as ResNet or Residual Network. — Every consecutive winning architecture uses more layers in a deep neural network to lower the error rate after the first CNN-based architecture (AlexNet) that won the ImageNet 2012 competition. This is effective for smaller numbers of layers, but when we add more layers, a typical deep learning issue known as…

Just a few weeks ago, YOLO v7 came into the limelight by beating all the existing object detection models to date. Anyone who has worked in Object detection has heard about YOLO. It’s been here for a while now, and to date, we have seen a lot of YOLO versions…

When beginning to build your first neural network, the process seems akin to feeling around for a needle in a haystack, blindfolded. …

Reinforcement Learning is one of the most intricate fields of Machine Learning, due to its mathematical complexity, as well as the ambitious tasks it tries to achieve. Simply put, the final goal of a RL algorithm is to make an agent capable of acting in an environment as to maximize…

How to use big data on a small computer using Tensorflow, Python and iterators — The amount of data in the current business world is increasing every day. There are new data sources to merge, more rows to append and new columns to concatenate. Unfortunately, for a typical data scientist or a machine learning engineer, the pace at which one can buy a new laptop…

Explaining their complex mathematical formula with working diagrams — Table of Contents · Recurrent Neural Networks (RNN) ∘ Vanilla RNN ∘ Long Short-term Memory (LSTM) ∘ Gated Recurrent Unit (GRU) · RNN Architectures · Attention ∘ Seq2seq with Attention ∘ Self-attention ∘ Multi-head Attention · Transformer ∘ Step 1. Adding Positional Encoding to Word Embeddings ∘ Step…

Overview of how object detection works, and where to get started — Note: This assumes you have a general idea of what convolutional neural networks are. If you need a refresher, this IBM post is excellent. You know how convolutional neural networks (or CNNs) detect and classify images. But you can expand on that CNN to detect objects within that image. How…