Researchers have developed a novel neuroevolutionary architecture search method called ONE-NAS for stock return prediction. This method evolves small recurrent networks that can be deployed on edge devices like Raspberry Pi for efficient online prediction. The evolved networks demonstrated superior performance compared to traditional models like LSTM and GRU, achieving significantly higher net returns and faster prediction times. AI
IMPACT Enables more efficient and cost-effective AI-powered financial forecasting on resource-constrained edge devices.
RANK_REASON The cluster contains research papers detailing a novel method for evolving neural networks for a specific application (stock prediction) and their deployment on edge devices.
Read on Hugging Face Daily Papers →
- alphaXiv
- arXiv
- CatalyzeX
- central processing unit
- DagsHub
- Gotit.pub
- graphics processing unit
- Hugging Face
- Raspberry Pi Zero
- Recurrent Neural Networks
- ScienceCast
- transformer
- gated recurrent unit
- long short-term memory
- Raspberry Pi 4B
- US
AI-generated summary · Google Gemini · from 5 sources. How we write summaries →