Skip to content
GCC AI Research

Training Deep Neural Networks in Tiny Subspaces

MBZUAI · Notable

Summary

Xiaolin Huang from Shanghai Jiao Tong University presented a talk at MBZUAI on training deep neural networks in tiny subspaces. The talk covered the low-dimension hypothesis in neural networks and methods to find subspaces for efficient training. It suggests that training in smaller subspaces can improve training efficiency, generalization, and robustness. Why it matters: Investigating efficient training methods is crucial for resource-constrained environments and can enable broader access to advanced AI.

Get the weekly digest

Top AI stories from the GCC region, every week.

Related

MedNNS: Supernet-based Medical Task-Adaptive Neural Network Search

arXiv ·

The paper introduces MedNNS, a neural network search framework designed for medical imaging, addressing challenges in architecture selection and weight initialization. MedNNS constructs a meta-space encoding datasets and models based on their performance using a Supernetwork-based approach, expanding the model zoo size by 51x. The framework incorporates rank loss and Fréchet Inception Distance (FID) loss to capture inter-model and inter-dataset relationships, improving alignment in the meta-space and outperforming ImageNet pre-trained DL models and SOTA NAS methods.

Low-Complexity NN Technology: Model and Precision Search, Acceleration Circuit, and Applications

MBZUAI ·

Researchers at National Taiwan University are developing low-complexity neural network technologies using quantization to reduce model size while maintaining accuracy. Their work includes binary-weighted CNNs and transformers, along with a neural architecture search scheme (TPC-NAS) applied to image recognition, object detection, and NLP tasks. They have also built a PE-based CNN/transformer hardware accelerator in Xilinx FPGA SoC with a PyTorch-based software framework. Why it matters: This research provides practical methods for deploying efficient deep learning models on resource-constrained hardware, potentially enabling broader adoption of AI in embedded systems and edge devices.

Can AI Learn Like Us? Unveiling the Secrets of Spiking Neural Networks

MBZUAI ·

MBZUAI Ph.D. graduate Hilal Mohammad Hilal AlQuabeh researched methods to improve the efficiency of machine learning algorithms, specifically focusing on pairwise learning and multi-instance learning. Pairwise learning teaches AI to make decisions by comparing options in pairs, useful for ranking and anomaly detection. Multi-instance learning involves learning from sets of data points, applicable in areas like drug discovery. Why it matters: Optimizing AI for low-resource environments expands its accessibility and applicability in critical sectors like healthcare and remote area operations.

Parameter-Efficient Fine-Tuning for NLP Models

MBZUAI ·

The article discusses parameter-efficient fine-tuning methods for large NLP models, highlighting their importance due to the increasing size and computational demands of state-of-the-art language models. It provides an overview of these methods, presenting them in a unified view to emphasize their similarities and differences. Indraneil, a PhD candidate at TU Darmstadt's UKP Lab, is researching parameter-efficient fine-tuning, sparsity, and conditional computation methods to improve LLM performance in multilingual, multi-task settings. Why it matters: Efficient fine-tuning techniques are crucial for democratizing access to and accelerating the deployment of large language models in the region and beyond.