Search Results for author:
Found 10 papers, 2 papers with code
Sisyphus: A Cautionary Tale of Using Low-Degree Polynomial Activations in Privacy-Preserving Deep Learning
In this work, we ask: Is it feasible to substitute all ReLUs with low-degree polynomial activation functions for building deep, privacy-friendly neural networks?
Circa: Stochastic ReLUs for Private Deep Learning
In this paper we re-think the ReLU computation and propose optimizations for PI tailored to properties of neural networks.
DeepReDuce: ReLU Reduction for Fast Private Inference
This paper proposes DeepReDuce: a set of optimizations for the judicious removal of ReLUs to reduce private inference latency.
Modeling Data Reuse in Deep Neural Networks by Taking Data-Types into Cognizance
arithmetic intensity, does not always correctly estimate the degree of data reuse in DNNs since it gives equal importance to all the data types.
DeepPeep: Exploiting Design Ramifications to Decipher the Architecture of Compact DNNs
The remarkable predictive performance of deep neural networks (DNNs) has led to their adoption in service domains of unprecedented scale and scope.
On the Demystification of Knowledge Distillation: A Residual Network Perspective
Surprisingly, in some cases, they surpass the accuracy of baseline networks even with the inferior teachers.
E2GC: Energy-efficient Group Convolution in Deep Neural Networks
We show that, at comparable computational complexity, DNNs with constant group size (E2GC) are more energy-efficient than DNNs with a fixed number of groups (F$g$GC).
ULSAM: Ultra-Lightweight Subspace Attention Module for Compact Convolutional Neural Networks
Our method of subspace attention is orthogonal and complementary to the existing state-of-the-arts attention mechanisms used in vision models.
DRACO: Co-Optimizing Hardware Utilization, and Performance of DNNs on Systolic Accelerator
The number of processing elements (PEs) in a fixed-sized systolic accelerator is well matched for large and compute-bound DNNs; whereas, memory-bound DNNs suffer from PE underutilization and fail to achieve peak performance and energy efficiency.
The Ramifications of Making Deep Neural Networks Compact
Reducing the number of parameters in DNNs increases the number of activations which, in turn, increases the memory footprint.
