Junaid Farooq

National Institute of Technology Srinagar

Papers

1

Total Citations

5

H-Index

1

About

Junaid Farooq is a researcher at the forefront of machine learning and time-series forecasting, with a particular focus on addressing the critical challenge of error accumulation in long-term predictions. His most cited work introduces a novel multiscale autoencoder-RNN architecture that mitigates the compounding errors inherent in autoregressive forecasting models, a problem that has long plagued applications from natural language processing to high-dimensional dynamical systems. By integrating a multiscale autoencoder with recurrent neural networks, Farooq’s approach enables more stable and accurate long-horizon predictions, directly tackling the instability that arises when models iteratively feed their own outputs back as inputs. This contribution is especially impactful for fields requiring reliable long-term forecasts, such as climate modeling, financial markets, and complex system monitoring. With his paper already garnering early citations, Farooq’s work signals a promising trajectory in advancing robust, scalable forecasting methods. His research not only deepens theoretical understanding of recurrent architectures but also offers practical solutions for real-world deployment, making him a rising voice in the machine learning community.

Research Focus

Key Achievements

1
H-Index
1
Papers
5
Total Citations
5
Avg Citations/Paper
🏆 Most Cited Paper
Multiscale Autoencoder-RNN Architecture for Mitigating Error Accumulation in Long-Term Forecasting
5 citations · 2023
📈 Most Prolific Year: 2023 (1 Papers)
🤝 Key Collaborators: 2
🏛 Institutions: National Institute of Technology Srinagar

Top Papers

  1. 1

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 12 days ago