And here is the final result with 5 recommended books and their respective scores. Code: https://
github.com/PacktPublishin
g/Hands-On-Graph-Neural-Networks-Using-Python/blob/main/Chapter17/chapter17.ipynb
… You'll find two other advanced use cases, related to time series forecasting and anomaly detection (the topic of my PhD!).
@maximelabonne
-
Graph Neural Networks: Book Recommendations and Advanced Applications
By
–
-
GNN Guide: Building Recommender Systems with LightGCN
By
–
This book is carefully crafted to provide a step-by-step guide for those new to the world of #GNN, while also offering advanced use cases and examples. For example, the following BookCrossing dataset is used to build a recommender system using LightGCN.
-
Graph Neural Networks Hands-On Guide Released with Python Code
By
–
I am thrilled to announce the release of my book, Hands-On Graph Neural Networks! It's been almost a year's worth of hard work, research, and collaboration with fellow experts in the field. The entire code is available on GitHub: https://
github.com/PacktPublishin
g/Hands-On-Graph-Neural-Networks-Using-Python
… #AI #Python -
Human Data vs Synthetic: Instructions Matter More Than Outputs
By
–
This idea of generating data from seeds sounds wrong: it creates lower quality data than human conversations. I think a better approach would be to retro-engineer humanly written text to get instructions. The main question is are instructions more important than outputs? #llama
-
Twitter Bot for Paper Recommendations Using AI
By
–
I used it to make a Twitter bot that recommends me papers, but I kept ignoring the recommendations…
-
Training LLMs to Use Multiple LLMs as Tools
By
–
– Toolformer showed you can train LLMs to use tools. – HuggingGPT showed that you can use LLMs as tools. Who wants to train an LLM that uses other LLMs that can use tools? Can 100+ small LLMs outperform #GPT4?
-
RWKV: RNN-based LLM combining RNNs and Transformers capabilities
By
–
RWVK: an #RNN-based LLM Feels like the MLP-Mixer moment for LLMs, combining the best of RNNs (longer sequences) and #Transformers (parallelization). The Raven chatbot is impressive and on par with recent models like GPT4All. https://
github.com/BlinkDL/RWKV-LM -
Pausing AI Development: Practical Implementation Challenges Explained
By
–
My favourite part in the public discourse about #AI is the idea that we should "pause" it. Like okay party's over, everybody goes home now! I've never seen anyone explaining how that'd work in practice.
-
LinkedIn text-to-video feature: Where is the promised capability?
By
–
Where is the text2video LinkedIn promised me?
-
GPT-4 Used for Academic Writing Raises Quality Concerns
By
–
They say at the end of the paper "GPT-4 was used for help with wording, formatting, and styling throughout this work." Maybe that's why it's so bland and generic! 🙂