AI/ML

Transparency, disclosure, and publication-level guidelines

Elicit uses machine learning to help you with your research: find papers, extract key claims, summarize, brainstorm ideas, and more.

You can use CoPilot from SciSpace as your research assistant to summarize research articles, find an article's limitations, ask specific research questions, and explain journal articles. Get the 30-day Research Jumpstart Guide: https://www.sciencegradschoolcoach.com/30day-research-guide Check Out SciSpace Co-Pilot: https://typeset.io/ Watch More: Organize Research Article Summaries: https://youtu.be/Qw6PdEVSU5c Summarize Research Articles with Scholarcy: https://youtu.be/Qw6PdEVSU5c Summarize Research Articles with Paper Digest: https://youtu.be/0dZ5hv8jpnQ In this video, I will walk you through how to use SciSpace and their new AI research assistant copilot. You can find research articles through their search bar or upload pdfs to their site. Then, we jump into CoPilot which is an AI research assistant and honestly one of the best that I have seen! CoPilot can share research article summaries, research article limitations, what is unique about this article, and the key takeaways of this article. Then, you can ask specific questions like if you do not know what a word in a research article is. Finally, CoPilot can explain research articles to you in plain English which is a massive game changer. --------------------------------------------------------------------------------------------------------------------------- Follow me: Twitter: https://twitter.com/scigradcoach Instagram: https://www.instagram.com/scigradcoach/ TikTok: https://www.tiktok.com/@scigradcoach Buy Me A Coffee: https://www.buymeacoffee.com/scigradcoach Free Resources: https://www.sciencegradschoolcoach.com/resources Courses: Research Accelerator: https://www.sciencegradschoolcoach.com/research-accelerator Write Your Research Article: https://www.sciencegradschoolcoach.com/Write-Your-Research-Article My Filming Setup: Video Editing: https://www.alanalrister.com/descript DISCLAIMER: Links included in this description might be affiliate links. If you purchase a product or service with the links that I provide I may receive a small commission. There is no additional charge to you. Timecodes 00:00 How to use SciSpace CoPilot 00:40 Searching for research articles 01:54 Upload Research Articles in SciSpace 02:38 SciSpace Co-Pilot 03:19 Summarizing Research Articles 04:30 What is unique about this paper? 04:58 Finding a Research Articles Conclusions 05:04 Research Articles Limitations 06:41 Research Article Specific Questions 08:43 Explaining a Research Article

Your platform to explore and explain papers. Search for 270M+ papers, understand them in simple language, and find connected papers, authors, topics.

Quick tutorial using Python, OpenAI’s GPT-3, and Streamlit

archived 23 Jan 2023 20:03:37 UTC

CNET's AI-generated articles appear to show deep structural similarities, amounting to plagiarism, with previously published work elsewhere.

Download, parse, and convert raw Wikimedia data into standard formats. - kensho-technologies/kwnlp-preprocessor: Download, parse, and convert raw Wikimedia data into standard formats.

Chatbots can help to provide real-time customer support and are a valuable asset in many industries. When you understand the basics of the ChatterBot library, you can build and train a self-learning chatbot with just a few lines of Python code.

GitHub is where people build software. More than 94 million people use GitHub to discover, fork, and contribute to over 330 million projects.

In this blog, we’d love to talk about the different approaches to developing a mental chatbot. Read on to learn how to create a therapeutic bot that could really help your patients instead of telling them to kill themselves (more on that below). We’ll discuss some of the best practices and various tools at your […]

A Computer Science portal for geeks. It contains well written, well thought and well explained computer science and programming articles, quizzes and practice/competitive programming/company interview Questions.

Wizard of Wikipedia is a large dataset with conversations directly grounded with knowledge retrieved from Wikipedia. It is used to train and evaluate dialogue systems for knowledgeable open dialogue with clear grounding

archived 23 Jan 2023 12:29:23 UTC

archived 23 Jan 2023 12:33:44 UTC

Explore and run machine learning code with Kaggle Notebooks | Using data from No attached data sources

by Jean-Louis Gassée

Not sure what book to read next? Let artificial intelligence find the next book for you to read. Type in the titles of books you like and see what book recommendations AI will find for you out of more than a million titles. Enjoy reading!

Galactica: https://galactica.org/ Explain Paper: https://www.explainpaper.com/ Elicit: https://elicit.org/

Other Red Ventures sites will also pause the use of AI writing tools.

I hate monopolies and welcome our AI overlords

“Everyone’s got their knives sharpened," says one insider.

With just a text description, AI can generate art or even photorealistic images. Explore the most powerful AI image generators.

ChatGPT has captured LLM headlines and amazed the AI community with its extensive natural language processing capabilities. A new LLM from Anthropic called Claude is competitive with ChatGPT and offers great promise. We evaluate both models head to head and give you our thoughts on how they compare.

The AI bot that CNET is using to churn out personal finance articles has a relatable problem: it keeps making dumb mistakes.

It has begun.

PyTorch uses the new Metal Performance Shaders (MPS) backend for GPU training acceleration.

Setup PyTorch on Mac/Apple Silicon plus a few benchmarks. - mrdbourke/pytorch-apple-silicon: Setup PyTorch on Mac/Apple Silicon plus a few benchmarks.

We build a Generatively Pretrained Transformer (GPT), following the paper "Attention is All You Need" and OpenAI's GPT-2 / GPT-3. We talk about connections to ChatGPT, which has taken the world by storm. We watch GitHub Copilot, itself a GPT, help us write a GPT (meta :D!) . I recommend people watch the earlier makemore videos to get comfortable with the autoregressive language modeling framework and basics of tensors and PyTorch nn, which we take for granted in this video. Links: - Google colab for the video: https://colab.research.google.com/drive/1JMLa53HDuA-i7ZBmqV7ZnA3c_fvtXnx-?usp=sharing - GitHub repo for the video: https://github.com/karpathy/ng-video-lecture - nanoGPT repo: https://github.com/karpathy/nanoGPT - my website: https://karpathy.ai - my twitter: https://twitter.com/karpathy - our Discord channel: https://discord.gg/3zy8kqD9Cp Supplementary links: - Attention is All You Need paper: https://arxiv.org/abs/1706.03762 - OpenAI GPT-3 paper: https://arxiv.org/abs/2005.14165 - OpenAI ChatGPT blog post: https://openai.com/blog/chatgpt/ - The GPU I'm training the model on is from Lambda GPU Cloud, I think the best and easiest way to spin up an on-demand GPU instance in the cloud that you can ssh to: https://lambdalabs.com . If you prefer to work in notebooks, I think the easiest path today is Google Colab. Suggested exercises: - EX1: The n-dimensional tensor mastery challenge: Combine the `Head` and `MultiHeadAttention` into one class that processes all the heads in parallel, treating the heads as another batch dimension (answer is in nanoGPT). - EX2: Train the GPT on your own dataset of choice! What other data could be fun to blabber on about? (A fun suggestion if you like: train on all the possible 3-digit addition problems and predict the sum in the reverse order. Does your Transformer learn the correct addition algorithm? Does it correctly generalize to the validation set?). - EX3: Find a dataset that is very large, so large that you can't see a gap between train and val loss. Pretrain the transformer on this data, then initialize with that model and finetune it on tiny shakespeare with a smaller number of steps and lower learning rate. Can you obtain a lower validation loss by the use of pretraining? - EX4: Read some transformer papers and implement one additional feature or change that people seem to use. Does it improve the performance of your GPT? Chapters: 00:00:00 intro: ChatGPT, Transformers, nanoGPT, Shakespeare baseline language modeling, code setup 00:07:52 reading and exploring the data 00:09:28 tokenization, train/val split 00:14:27 data loader: batches of chunks of data 00:22:11 simplest baseline: bigram language model, loss, generation 00:34:53 training the bigram model 00:38:00 port our code to a script Building the "self-attention" 00:42:13 version 1: averaging past context with for loops, the weakest form of aggregation 00:47:11 the trick in self-attention: matrix multiply as weighted aggregation 00:51:54 version 2: using matrix multiply 00:54:42 version 3: adding softmax 00:58:26 minor code cleanup 01:00:18 positional encoding 01:02:00 THE CRUX OF THE VIDEO: version 4: self-attention 01:11:38 note 1: attention as communication 01:12:46 note 2: attention has no notion of space, operates over sets 01:13:40 note 3: there is no communication across batch dimension 01:14:14 note 4: encoder blocks vs. decoder blocks 01:15:39 note 5: attention vs. self-attention vs. cross-attention 01:16:56 note 6: "scaled" self-attention. why divide by sqrt(head_size) Building the Transformer 01:19:11 inserting a single self-attention block to our network 01:21:59 multi-headed self-attention 01:24:25 feedforward layers of transformer block 01:26:48 residual connections 01:32:51 layernorm (and its relationship to our previous batchnorm) 01:37:49 scaling up the model! creating a few variables. adding dropout Notes on Transformer 01:42:39 encoder vs. decoder vs. both (?) Transformers 01:46:22 super quick walkthrough of nanoGPT, batched multi-headed self-attention 01:48:53 back to ChatGPT, GPT-3, pretraining vs. finetuning, RLHF 01:54:32 conclusions Corrections: 00:57:00 Oops "tokens from the _future_ cannot communicate", not "past". Sorry! :)