Search Results for author:
Found 16 papers, 5 papers with code
Revealing the Utilized Rank of Subspaces of Learning in Neural Networks
In our findings, we conclude that most models utilize a fraction of the available space.
Pruning for Improved ADC Efficiency in Crossbar-based Analog In-memory Accelerators
sparsity is then achieved by regularizing the variance of $L_{0}$ norms of neighboring columns within the same crossbar.
Memorization Through the Lens of Curvature of Loss Function Around Samples
Second, we inject corrupted samples which are memorized by the network, and show that these are learned with high curvature.
Samples With Low Loss Curvature Improve Data Efficiency
SLo-curves identifies the samples with low curvatures as being more data-efficient and trains on them with an additional regularizer that penalizes high curvature of the loss surface in their vicinity.
TOFU: Towards Obfuscated Federated Updates by Encoding Weight Updates into Gradients from Proxy Data
This is done via a central server that aggregates learning in the form of weight updates.
Encoding Hierarchical Information in Neural Networks helps in Subpopulation Shift
We show that learning in this structured hierarchical manner results in networks that are more robust against subpopulation shifts, with an improvement up to 3\% in terms of accuracy and up to 11\% in terms of graphical distance over standard models on subpopulation shift benchmarks.
Intra-class Mixup for Out-of-Distribution Detection
This reduces the separability of in-distribution data from OoD data.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
Spatio-Temporal Pruning and Quantization for Low-latency Spiking Neural Networks
Moreover, they require 8-14X lesser compute energy compared to their unpruned standard deep learning counterparts.
Gradient Projection Memory for Continual Learning
The ability to learn continually without forgetting the past tasks is a desired attribute for artificial learning systems.
DCT-SNN: Using DCT To Distribute Spatial Information Over Time for Low-Latency Spiking Neural Networks
Notably, DCT-SNN performs inference with 2-14X reduced latency compared to other state-of-the-art SNNs, while achieving comparable accuracy to their standard deep learning counterparts.
Exploring Vicinal Risk Minimization for Lightweight Out-of-Distribution Detection
We utilize mixup in two ways to implement Vicinal Risk Minimization.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
DCT-SNN: Using DCT to Distribute Spatial Information over Time for Learning Low-Latency Spiking Neural Networks
Notably, DCT-SNN performs inference with 2-14X reduced latency compared to other state-of-the-art SNNs, while achieving comparable accuracy to their standard deep learning counterparts.
TREND: Transferability based Robust ENsemble Design
In this work, we study the effect of network architecture, initialization, optimizer, input, weight and activation quantization on transferability of adversarial samples.
SPACE: Structured Compression and Sharing of Representational Space for Continual Learning
A minimal number of extra dimensions required to explain the current task are added to the Core space and the remaining Residual is freed up for learning the next task.
Constructing Energy-efficient Mixed-precision Neural Networks through Principal Component Analysis for Edge Intelligence
The `Internet of Things' has brought increased demand for AI-based edge computing in applications ranging from healthcare monitoring systems to autonomous vehicles.
A Low Effort Approach to Structured CNN Design Using PCA
We demonstrate the proposed methodology on AlexNet and VGG style networks on the CIFAR-10, CIFAR-100 and ImageNet datasets, and successfully achieve an optimized architecture with a reduction of up to 3. 8X and 9X in the number of operations and parameters respectively, while trading off less than 1% accuracy.
