Weather Data; Aleatoric & Epistemic Uncertainty — Performances of Deep Neural Networks (DNNs) rely on the ability to progressively build and extract features from large data. Though these deep models are usually adaptive the performance depends on the data distribution. The robustness property is important in various applications such as computer vision tasks, eg. autonomous driving, because…

Finding Prime Factors of Integer using Quantum Computer — We all have possibly read stories and news about the encryption schemes to protect our credit cards, confidential files will be broken by the advancement of quantum computing technology in recent years. Here’s another recent Nature article (from this year, February) about it and how…

Self-Attention Mechanism and Goodbye Convolution! — When Transformer Network came out, initially it became the go to model for NLP tasks. ‘An Image is Worth 16X16 Words’ which was presented in International Conference for Representation Learning (ICLR) 2021, by Alex Dosovitskiy et.al. showed for the first time how Transformer can be implemented for Computer Vision tasks…

Determine Phase of an Eigenvector of a Unitary Operator — Quantum Phase Estimation (QPE) is an algorithm that’s used to estimate the phase (or eigenvalue) of an eigenvector of a unitary operator. Since this post will use many important concepts discussed in the Quantum Fourier Transform post, please check it for a review. …

Probability, Likelihood and TensorFlow Probability Library — Both Naive Bayes and Logistic Regression are quite commonly used classifiers and in this post, we will try to find and understand the connection between these classifiers. We will also go through an example using Palmer Penguin Dataset which is available under…

Did Ray Bradbury Foresee What’s Coming? — Sunday mornings are quite serene; morning coffee, surfing news for short time, then going out for a stroll around the neighbourhood with my cat. Sunday, 1st August 2021 was a bit different. I guess I forgot to put sugar in my coffee and it tasted unusually bitter but, this bitterness…

Deal with Class Imbalance and Use Pre-Trained Model Effectively — In the past few years, we have seen a rapid increase in using Deep Learning for medical diagnosis in various forms, specially in the analysis of medical images. Here we will set up a pipeline to classify chest x-ray images of patients with and without pneumonia. The complete dataset is…

Using Pre-trained Model to Deploy Your Classifier Faster — Cassava is widely cultivated as an annual crop and it is one of the major source of carbohydrates and food, specially in Sub-Saharan Africa. But, Cassava crops are quite vulnerable to various diseases, which threaten to destabilize food security in a large region. Here, we would like to use deep…

The equation that describes the shapes of avian Eggs — A standard formula for describing any bird’s egg in nature is here, and the research report is published recently in the Annals of the New York Academy of Sciences. Eggs are in a sense representation of perfect shape considering the evolution process because they are optimized to cover an embryo…