Prabin Nepal

Augmenting Large Language Models: Expanding Context and Enhancing Relevance

machine-learning

NLP

deep-learning

LLM

With the rise of ChatGPT and other large language models (LLMs), the potential for AI to surpass human capabilities has become a topic of both fascination and concern. While…

Brief overview of GPT-4

machine-learning

NLP

deep-learning

Since the release of ChatGPT, there has been significant interest and discussion within the broader AI and natural language processing communities regarding its…

Text Summarization NLP

NLP

deep-learning

Text summarization is one of the Natural Language Processing (NLP) tasks where documents/texts are shortened automatically while holding the same semantic meaning.…

Autocorrect and Minimum Edit Distance

NLP

deep-learning

This is my brief note from DeepLearning.AI’s NLP Specialization Course.

Illustrated Vision Transformers

computer-vision

deep-learning

Ever since Transformer was introduced in 2017, there has been a huge success in the field of Natural Language Processing (NLP). Almost all NLP tasks use Transformers and…

Paper Explanation: A Simple Framework for Contrastive Learning of Visual Representations (simCLR)

Various self-supervised learning methods have been proposed in recent years for learning image…

Deep Residual Learning for Image Recognition (ResNet paper explained)

Deep Neural Networks tend to provide more accuracy as the number…

Self-supervised Learning

deep-learning

self-supervised-learning

I have been exploring self-supervised learning and been through papers and blogs to understand it. Self-supervised learning is considered the next big thing in deep learning…

MobileNet Architecture Explained

deep-learning

In this blog post, I will try to write about the MobileNets and its architecture. MobileNet uses depthwise separable convolutions…

Neural style transfer and its working

Have you ever used an app called Prisma that styles your image using popular paintings and…

Deep Convolutional Generative Adversarial Networks (DCGANs)

computer-vision

deep-learning

DCGAN (Deep Convolutional General Adversarial Networks) uses convolutional layers in its design.

General Adversarial Networks (GANs)

computer-vision

deep-learning

“General Adversarial Nets is the most interesting idea in the last 10 years in machine learning”. This was the statement from Yann LeCun regarding GANs when Ian…

Paper Explanation: Going deeper with Convolutions (GoogLeNet)

computer-vision

deep-learning

Google proposed a deep Convolution Neural Network named inception that achieved top results for classification and detection in ILSVRC 2014.

VGGNet Architecture Explained

computer-vision

deep-learning

VGGNet is a Convolutional Neural Network architecture proposed by Karen Simonyan and Andrew Zisserman of University of…

AlexNet Architecture Explained

computer-vision

deep-learning

AlexNet famously won the 2012 ImageNet LSVRC-2012 competition by a large margin (15.3% vs 26.2%(second place) error rates). Here is the link to original paper.