Supercomputers are a class of high-performance systems comprised of multiple central processing units (CPUs) in order to achieve high computational rates. They achieve fastest performance at a given time by using vector arithmetic which enables the system to operate on pairs of lists of numbers instead of simple pairs of numbers. For instance, if we
Quantum computing in supercomputers Read More »
Introduction Probability distributions are cornerstones in the theory of machine learning. The entire field of machine learning is often theoretically viewed or explained from a probabilistic perspective. Compared to the linear algebraic point of view, the probabilistic perspective gives formulations of machine learning algorithms that are more impressive. Binomial distribution is one of the many
Binomial Distribution Read More »
Frequentist and Bayesian are two schools of thought in probability theory. Let us look at the difference between them. Bayesian and frequentist approaches are two major frameworks in statistics for analyzing data and making statistical inference. The frequentist approach is based on the idea of probability as the long-term frequency of an event in repeated
Frequentist and Bayesian: A Quick Comparison Note Read More »
Dream for a computer storage device which performs as fast as static RAM (SRAM), delivers the cost effectiveness of dynamic RAM (DRAM), promises the non-volatility of flash memory, combined with added benefits of longevity, denser storage, durability and stability. Let’s discuss whether spin transfer torque based Random access Memory (STT-RAM) devices can help to realize
Spin Transfer Torque based Magnetic Memory Devices Read More »
The field of information theory defines entropy as a measure of average information a random variable takes. As we know the random variable is one whose possible outcome states are not deterministic. We cannot predict its behavior exactly in an analytical form. In such cases, we can only look at the patterns of its outcome
Entropy Simplified Read More »
This article is a tutorial on the algorithm called active Learning with uncertainty Sampling. Introduction Availability of mass quantities of digital data and feasible computing power brought to the creation of learning algorithms. These learning algorithms have been benchmarked to perform specialized tasks such as classification, object detection, image segmentation, etc. The key assumption here
Active Learning with Uncertainty Sampling from Scratch Read More »
This article is a review of active learning which is a subfield of machine learning Introduction The field of Machine Learning (ML) broadly deals with giving computers the ability to do tasks like humans. We are seeing a human-level performance in specialized tasks such as speech recognition, image recognition, etc. Many sub-fields of ML are
A Brief Review of Active Learning Read More »
The topic I wish to talk in this post is about Mathematical maturity. It is connected to the abstract nature of mathematics and humans’ endeavor to cope with it. Let me start by asking you a question. Have you ever seen a circle in real-life?. You might say yes because we all draw many in
Mathematical maturity Read More »
Why does it need to look for an alternate cooling technology? Cooling appliances based on thermodynamic cycle till 1995 used to produce many toxic components Chloroflurocarbon CFC), Hydrochloroflurocarbon (HCFC), potent greenhouse gases (GHG) and other ozone depleting substances (ODC). After gradual prohibition of such gases, the cooling appliances till date producing HFCs which have no
Magnetic Refrigeration Technology Read More »
What calls for an advanced technology based on electron spin? Electronics use the property of electrons called charge to encode information. One way computers store information is by using RAM. RAM is comprised of billions of capacitors and to store information computer sends a large number of electrons which are absorbed by the capacitor plate
Spintronics: Concepts Based Introduction Read More »