Deep Learning

Run Llama3.1-8B (LLM) on DigitalOcean CPU droplet

In this guide at OpenGenus.org, we present the steps to setup the minimum required DigitalOcean CPU droplet, download Llama3.1-8B-Instruct model, prepare the script to run it on a sample input and generate the output. The computation time can vary from 2 to 10 minutes (or beyond).

Deep Learning

DL1943 Deep Learning Cheatsheet

The book "Deep Learning: DL1943 Cheatsheet: DL/AI/ML Research, Engineering, Optimization & System Design" is the only book you need to master Deep Learning (DL) concepts.

PyTorch

Understanding the differences and use Cases of torch.Tensor.max and torch.max in PyTorch

torch.Tensor.max is an instance method that applies directly to a torch.Tensor object and is mainly used to find maximum values within a single tensor. torch.max is a module-level function used to compare two tensors element-wise.

Deep Learning

Retrieval Augmented Generation (Concepts)

The RAG concept was first introduced in the paper "Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks" by Patrick Lewis and team at Facebook AI Research, which caught the attention of AI developers and industrial scientists.

Deep Learning

Bilinear Upsampling

In this OpenGenus article, let us discuss Bilinear Upsampling which pops up quite bit in regards to image manipulation and processing in a greater detail.

PyTorch

slice_scatter op in PyTorch

`torch.slice_scatter` is a tensor manipulation function in PyTorch that allows us to embed values from one tensor into another at specified locations. This operation generates a new tensor with fresh storage rather than modifying the original tensor.

PyTorch

Designing ResNet50 in PyTorch

The core architectural innovation is the use of residual blocks with shortcut connections (or skip connections).

Deep Learning

Kolmogorov-Arnold Networks

Kolmogorov-Arnold Networks (KANs) have emerged as a promising advancement in the field of neural networks, offering enhanced interpretability, efficiency, and adaptability compared to traditional architectures like the Multi-Layer Perceptron (MLPs).

Deep Learning

Implementing Simple CNN model in PyTorch

In this OpenGenus article, we will learn about implementing a simple CNN model using PyTorch Deep Learning framework.

PyTorch

Internal Implementation of Tensors in PyTorch

In this OpenGenusarticle, we'll delve into the internals of how tensors are implemented in PyTorch, referencing the code from various components of the PyTorch source code repository.

Deep Learning

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.

Deep Learning

Guide to Deep Learning Model Training and Quantization

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.

Deep Learning

INT4 Quantization (with code demonstration)

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.

Machine Learning (ML)

Markov Chain Neural Network (MCNN)

In this OpenGenus article, we will explore Markov chains, their intersections with neural networks, and a simple implementation of a Markov chain neural network (MCNN). We will also take a look at their applications.

Deep Learning

Basics of using PyTorch

PyTorch is an open-source deep learning framework primarily developed by Facebook's AI Research lab (FAIR).

Deep Learning

Position wise Feed-Forward Networks

Position-wise Feed-Forward Networks (FFN) are a crucial component in various sequence-to-sequence models, especially in the context of natural language processing and tasks like machine translation.

Machine Learning (ML)

Why convexity is important in Machine Learning?

In machine learning, convexity plays a crucial role in optimization problems. Convex optimization problems are desirable because they ensure the existence of a unique global minimum.

System Design

Vector Databases: Long-term Memory of LLMs

In the rapidly evolving landscape of artificial intelligence, Large Language Models (LLMs) have become the cornerstone of various applications, from natural language processing to content generation.

Machine Learning (ML)

Sentiment Analysis For Mental Health Sites and Forums

This OpenGenus article delves into the crucial role of sentiment analysis in understanding emotions on mental health platforms. Featuring a Python program using NLTK's VADER, it explains the importance of comprehending user emotions for early intervention and personalized user experiences.

Deep Learning

Introduction to Multi-Agent Systems (MAS)

Multi-Agent Systems (MAS) consist of autonomous agents that interact with each other and their environment to achieve individual or collective goals.

Machine Learning (ML)

ML model to predict Waiter’s Tip

This OpenGenus article explores the application of machine learning techniques in predicting waiter tips based on factors such as total bill, day and time. Written in Python, the code employs one-hot encoding and Linear Regression, offering an understanding of these concepts.

Deep Learning

Adaptive Recommender Systems

Adaptive recommender systems are intelligent algorithms designed to analyze user behavior, preferences, and interactions with a platform to deliver personalized recommendations.

Machine Learning (ML)

Regression dilution

In this article at OpenGenus, we will explore the concept of regression dilution, its implications in various real-world applications. We will discuss when it is crucial to correct for these errors and when it may be appropriate to skip correction.

Deep Learning

ML model to predict Fuel Efficiency [project]

The goal of the fuel efficiency project at OpenGenus is to predict the fuel efficiency of a vehicle based on various input features.

Deep Learning

MobileNet V3 model

MobileNetV3 is a neural network architecture designed to provide efficient deep learning capabilities on resource-constrained mobile devices. We delve into the essence of MobileNetV3, exploring its history, applications, advantages, disadvantages, and underlying architecture.