- Trending Categories
- Data Structure
- Networking
- RDBMS
- Operating System
- Java
- MS Excel
- iOS
- HTML
- CSS
- Android
- Python
- C Programming
- C++
- C#
- MongoDB
- MySQL
- Javascript
- PHP
- Physics
- Chemistry
- Biology
- Mathematics
- English
- Economics
- Psychology
- Social Studies
- Fashion Studies
- Legal Studies
- Selected Reading
- UPSC IAS Exams Notes
- Developer's Best Practices
- Questions and Answers
- Effective Resume Writing
- HR Interview Questions
- Computer Glossary
- Who is Who
Found 548 Articles for Algorithms
24 Views
The present article breaks down the concept of K-Means, a prevalent partitioning method, from its algorithmic framework to its pros and cons, helping you better grasp this sophisticated tool. Let's dive into the captivating world of K-Means clustering! K-Means Algorithm The K-Means algorithm is a centroid-based technique commonly used in data mining and clustering analysis. How K-Means Works? The K-Means Algorithm, a principle player in partitioning methods of data mining, operates through a series of clear steps that move from basic data grouping to detailed cluster analysis. Initialization − Specify the number of clusters 'K' to be created. This ... Read More
105 Views
Introduction In a time characterized by data deluge and data intricacy, extricating important bits of knowledge from colossal datasets has advanced from an extravagance to a need. Information mining methods serve as the establishment of this transformative handle, and among its strongest devices is cluster examination. This article sets out on an investigation of the scene of cluster examination, exploring through its crucial standards, enlightening its points of interest, recognizing its inherent requirements, recognizing its impediments, unraveling its different applications, dismembering its centrality in the midst of challenges, and coming full circle in a comprehensive understanding of its part in shaping ... Read More
233 Views
Introduction Data mining, a method for drawing important conclusions and knowledge from huge datasets, heavily relies on data cleaning. Ensuring that the input data is precise, consistent, and comprehensive is important before we can develop the potential of data mining algorithms. Raw collected data usually contains errors due to human mistakes or system glitches such as missing values or incorrect formatting. Data mining refers to the process of discovering patterns, relationships, and valuable insights from large quantities of raw or unstructured data. Data Mining – Data Cleaning Data cleaning is an integral part of any successful data mining exercise as ... Read More
92 Views
Introduction The idea of filter groups, also known as grouped convolution, was first explored by AlexNet in 2012. This creative solution was prompted by the necessity to train the network using two Nvidia GTX 580 GPUs with 1.5GB of memory each. Challenge: Limited GPU Memory During testing, AlexNet's creators discovered it needed a little under 3GB of GPU RAM to train. Unfortunately, they couldn't train the model effectively using both GPUs because of memory limitations. The Motivation behind Filter Groups In order to solve the GPU memory problem, the authors came up with filter groups. By optimizing the model's parallelization ... Read More
36 Views
Introduction LSTM, which stands for Long Short-Term Memory, is an advanced form of recurrent neural network (RNN) specifically designed to analyze sequential data like text, speech, and time series. Unlike conventional RNNs, which struggle to capture long-term dependencies in data, LSTMs excel in understanding and predicting patterns within sequences. Conventional RNNs face a significant challenge in retaining crucial information as they process sequences over time. This limitation hampers their ability to make accurate predictions based on long-term memory. LSTM was developed to overcome this hurdle by enabling the network to store and maintain information for extended periods. Structure of an ... Read More
42 Views
Introduction In recent years, deep neural networks (DNN) have made significant progress in reinforcement learning algorithms. In order to achieve desirable results, these algorithms, however, suffer from sample inefficiency. A promising approach to tackling this challenge is episodic memory-based reinforcement learning, which enables agents to grasp optimal actions rapidly. Using episodic memory to enhance agent training, Episodic Memory Deep Q-Networks (EMDQN) are a biologically inspired RL algorithm. Research shows that EMDQN significantly improves sample efficiency, thereby improving the chances of discovering effective policies. It surpasses both regular DQN and other episodic memory-based RL algorithms by achieving state-of-the-art performance on Atari ... Read More
73 Views
Density Estimation is an essential part of both machine learning and statistics. It means getting the probability density function (PDF) of a group. It is necessary for many things, like finding outliers, putting things into groups, making models, and finding problems. Based on deep learning, this study looks at all the ways to measure old and new density. Traditional Density Estimation Methods Histograms Whether you need to know in a hurry whether your data collection is complete, a histogram is the way to go. They take the data range and chunk it up into categories called " bins " to determine ... Read More
85 Views
Transformer models have progressed much in natural language processing (NLP), getting state-of-the-art results in many tasks. But Transformers' computational complexity and memory needs increase by a factor of four with the length of the input sequence. This makes it hard to handle long sequences quickly. Researchers have developed Sparse Transformers, an extension of the Transformer design that adds sparse attention mechanisms, to get around these problems. This article looks at the idea of Sparse Transformers, with a focus on Stride and Fixed Factorized Attention, two methods that help make these models more efficient and effective. Transformer Recap Before getting into ... Read More
34 Views
Introduction The brain is the most complicated organ and is used for various scientific studies. The human brain is studied and the prototype is implemented for artificial intelligence (AI) and machine learning (ML). The hippocampus is an essential part of the brain. It helps us learn, remember, and find our way around. Researchers have tried to create an Artificial Hippocampus Algorithm (AHA) that can copy the functions and skills of the hippocampus in ML systems. This article discusses AHA, its mechanisms, scopes, and limitations. Motivation for Artificial Hippocampus Algorithm The goal of making an AHA is to improve the ability ... Read More
125 Views
Steady State Genetic Algorithm (SSGA) is often used in machine learning and optimization tasks. It is a population-based, iterative search method based on the ideas behind natural evolution and genetics. SSGA works with a group of possible answers, shown as people or chromosomes. Here's how SSGA genetic Algorithm works Initialization − The algorithm starts by making a group called the starting population. Each person is a possible way to solve the problem at hand. Most of the time, the population is made or started randomly based on what we already know about the problem area. Evaluation − Everyone in ... Read More