Aditya Chatterjee's Blog, page 4

Memory Density Limits in Computers: Theoretical Boundaries and Practical Advances

Key TakeawaysRapid data growth requires memory technology that maximizes storage capacity, minimizes size, and maintains speed.Concepts such as the Bekenstein bound suggest that the amount of information stored in a physical space is fundamentally limited.As memory components shrink, they face physical problems such as quantum effects and thermal noise that affect reliability and performance.Traditional silicon-based memory such as DRAM and flash has its limits, with problems such as leakag...

as_strided op in PyTorch

So you've now finally begun working towards building your first network in PyTorch. You're working with tensors in the dataset, you wish to alter their shape, or do some form of operations. The as_strided() function in PyTorch can be very useful for this.

Table of Contents:

What is as_strided()?CNN operations with as_strided()Cautions with as_strided()Test your knowledgeKey takeaways

The pytorch as_strided function

Key Questions:

What does as_strided do?How do you determine the stride of...

Stepwise Regression

Say you're planning to work on a regression problem with a given dataset, you know how to build a regression model that predicts your desired output variable, but you are unsure about the importance of each variable. This is where our topic of this article comes in! We will be learning about stepwise regression- a technique that will help us find the best set of variables to choose for our linear regression.

Table of contents:

Introduction- Why use Stepwise Regression?Process: How does stepwis...

IPv6: Understanding its Development, Architectural Enhancements, and Current Adoption

Table of ContentsIntroduction1.1 Historical BackgroundObjectives of This ArticleIPv6 Architecture2.1 Address Structure2.2 Header Format2.3 Extension HeadersAddressing and Routing3.1 Address Allocation3.2 Routing Protocols3.3 Neighbor Discovery Protocol (NDP)Transition from IPv4 to IPv64.1 Dual Stack Approach4.2 Tunneling Mechanisms4.3 Translation TechniquesSecurity in IPv65.1 IPsec5.2 Privacy ExtensionsIPv6 adoptionConclusion1. Introduction

The Internet Prot...

Guide to Deep Learning Model Training and Quantization

Table of ContentAn OverviewSetting Up the EnvironmentMNISTBuild the ModelTrain the Model in FP32Quantize the Model to INT8Final Implementation and OutputEvaluate the Quantized ModelComparing FP32 and INT8 ModelsPerformanceAccuracyModel SizeConclusionAn Overview

In this OpenGenus article, I will be guiding you through training a sample convolutional neural network (ConvNet) with 5 convolutional layers for a specific task. The twist? We'll be exploring both FP32 (32-bit floating...

INT4 Quantization (with code demonstration)

TABLE OF CONTENTINT4 QuantizationImportanceWorking of INT4 QuantizationSimple DemonstrationFinal ImplementationINT4 VS INT8Quantization TechniquesTraining StrategiesINT4 Models: Accuracy & PerformanceUse CasePros & ConsConclusionKey PapersINT4 Quantization

INT4 quantization is a technique used to optimize deep learning models by reducing their size and computational costs. It achieves this by using 4-bit integers instead of 32-bit floating-point numbers.

This approach makes th...

Database Indexing

Table of ContentsDatabase Index and Its ImportanceTypes of IndexesManaging IndexesMonitoring Index UsageMaintaining IndexesDropping IndexesConclusionDatabase Index and Its Importance

Database indexing is a technique to enhance the speed of data retrieval in a database. An index is a data structure that allows quick access to rows in a table, similar to a book's index helping you find topics quickly without reading every page.

By creating an index on one or more columns, the database...

List and Dictionary Comprehension in Python

In this article, we will be discussing list and dictionary comprehension and it's relevance.

Table of Contents:

ListsDictionariesFor loopsConditional statementsList and Dictionary ComprehensionLists

Lists are important data structures in Python used for containing elements. These elements can be in the form of numbers, letters and alphabets. Elements can be appended, removed and inserted into these lists. Each element within the list can be accessed using the index of that element. They a...

Personality Prediction Through Machine Learning

An accurate comprehension of the world largely hinges on understanding what motivates the people living on it. A person's action or reaction to any issue is largely dependent on the answer to the question: What kind of a person he is?
In this OpenGenus article, we aim to create a Machine Learning model which can tell us exactly that.

ContentsThe Myers Briggs Type Indicator (MBTI)Algorithm : XGBoost ClassifierBuilding the ModelCode ImplementationApplicationsKey-TakeawaysThe Myers Briggs ...

Dynamic and Static dispatch in C++

A dispatch mechanism determines which function gets executed when called upon by an object. In this OpenGenus article, we will explore each of these mechanisms along their approach to overloading and polymorphism.

Table of contents:

OverviewVirtual functions and vtablesStatic dispatchDynamic dispatchLinking design patternsConclusionOverview

Static dispatch, also known as early binding or compile-time binding, is a technique where the decision about which function to call is made at com...