Isaac Kargar – Medium

Mar 1

WebGPT: Improving the factual accuracy of language models through web browsing

In this blog post, which is part of my blog post series on conversational AI and chatbots, I will review WebGPT proposed by OpenAI. Introduction WebGPT article discusses the challenge of long-form question-answering (LFQA) in natural language processing (NLP). LFQA systems have the potential to become a primary source of learning…

Deep Learning

5 min read

WebGPT: Improving the factual accuracy of language models through web browsing

Deep Learning

5 min read

Published in AIGuys

·Feb 26

Graphs to Graph Neural Networks: From Fundamentals to Applications — Part 1b: Graph Theory Fundamentals

In this post, which is the second post from my blog post series on Graphs, we will go over another 10 questions about graph theory fundamentals. You can find the previous post here: Graphs to Graph Neural Networks: From Fundamentals to Applications — Part 1a: Graph Theory… I decided to start a series of blog posts on Graphs and Graph Neural Networks (GNNs) to learn more about these topics…kargarisaac.medium.com

Graph

20 min read

Graph

20 min read

Published in AIGuys

·Feb 21

LaMDA: Language Models for Dialog Applications

Note: ChatGPT and other AI tools are used as assistants in this blog post. Introduction This paper proposes LaMDA, a family of transformer-based neural language models designed for dialog proposed by Google. These models’ sizes range from 2B to 137B parameters, and they are pre-trained on a dataset of 1.56T…

Chatbots

8 min read

LaMDA: Language Models for Dialog Applications

Chatbots

8 min read

Published in AIGuys

·Feb 17

Graphs to Graph Neural Networks: From Fundamentals to Applications — Part 1a: Graph Theory Fundamentals

I decided to start a series of blog posts on Graphs, Knowledge Graphs, and Graph Neural Networks (GNNs) to learn more about these topics. I thought it would also be fun to test ChatGPT and the new Bing, which I got access to recently, and see how they can help…

Deep Learning

19 min read

Graphs to Graph Neural Networks: From Fundamentals to Applications — Part 1a: Graph Theory…

Deep Learning

19 min read

Published in AIGuys

·Feb 11

BlenderBot v2

Note: ChatGPT and other AI writing assistant tools are used in this post to improve the writing quality. This article is part of my blog series on chatbots and conversational agents. In earlier posts, we reviewed ChatGPT, Meena, and BlenderBot v1. We will now review BlenderBot v2, which was developed…

NLP

12 min read

NLP

12 min read

Published in AIGuys

·Feb 4

SCENE: Reasoning about Traffic Scenes using Heterogeneous Graph Neural Networks

Encoding the driving scene in an autonomous driving system is a very important task that has not yet been solved completely. This work is one of the most recent ones that I found interesting among the many researchers who are working to encode driving scenes using graph neural networks. Let's…

Autonomous Cars

9 min read

SCENE: Reasoning about Traffic Scenes using Heterogeneous Graph Neural Networks

Autonomous Cars

9 min read

Published in AIGuys

·Jan 27

Recipes for building an open-domain chatbot: BlenderBot v1

In the previous blog post, we talked about Meena, a Google AI chatbot. In this post, I will review BlenderBot, the chatbot developed and open-sourced by Meta. I will go through the next versions of the BlenderBot in the next few posts. Let’s get started! Introduction BlenderBot is an open-domain…

Naturallanguageprocessing

8 min read

Naturallanguageprocessing

8 min read

Published in AIGuys

·Jan 17

Meena — Towards a Human-like Open-Domain Chatbot

Note: This blog post is written with the help of ChatGPT! I decided to start a series of blog posts on chatbots and conversational agents, diving into the world of AI-powered language models and their capabilities. In my first post, I review Meena, the conversational agent introduced by Google AI. …

Deep Learning

6 min read

Meena — Towards a Human-like Open-Domain Chatbot

Deep Learning

6 min read

Published in AIGuys

·Jan 14

Chinchilla: Training Compute-Optimal Large Language Models

The article investigates the optimal model size and the number of tokens for training a transformer language model under a given computation budget. They found that current large language models are undertrained, and by training over 400 language models with varying parameters and the number of tokens, they found that…

Deep Learning

5 min read

Chinchilla: Training Compute-Optimal Large Language Models

Deep Learning

5 min read

Published in DevOps.dev

·Jan 14

MLOps project — part 4b: Machine Learning Model Monitoring

We reviewed Evidently.AI and Seldon ALIBI Detect for model monitoring in our previous blog post. I will go through managed services on Google Cloud and AWS to do the model monitoring task. I like to emphasize the importance of MLOps parts using the following photo from a paper published by…

Machine Learning

13 min read

Machine Learning

13 min read