
Structured Convolutions for Efficient Neural Network Design
In this work, we tackle model efficiency by exploiting redundancy in the...
read it

Taxonomy and Evaluation of Structured Compression of Convolutional Neural Networks
The success of deep neural networks in many realworld applications is l...
read it

Federated Learning of User Authentication Models
Machine learningbased User Authentication (UA) models have been widely ...
read it

AI Benchmark: Running Deep Neural Networks on Android Smartphones
Over the last years, the computational power of mobile devices such as s...
read it

Gradient ℓ_1 Regularization for Quantization Robustness
We analyze the effect of quantizing weights and activations of neural ne...
read it

TimeGate: Conditional Gating of Segments in Longrange Activities
When recognizing a longrange activity, exploring the entire video is ex...
read it

Robust Data Association for Objectlevel Semantic SLAM
Simultaneous mapping and localization (SLAM) in an real indoor environme...
read it

Conditional Channel Gated Networks for TaskAware Continual Learning
Convolutional Neural Networks experience catastrophic forgetting when op...
read it

TRP: Trained Rank Pruning for Efficient Deep Neural Networks
To enable DNNs on edge devices like mobile phones, lowrank approximatio...
read it

Video Compression With RateDistortion Autoencoders
In this paper we present a a deep generative model for lossy video compr...
read it

Understanding StraightThrough Estimator in Training Activation Quantized Neural Nets
Training activation quantized neural networks involves minimizing a piec...
read it

LSQ+: Improving lowbit quantization through learnable offsets and better initialization
Unlike ReLU, newer activation functions (like Swish, Hswish, Mish) that...
read it

A Data and Compute Efficient Design for LimitedResources Deep Learning
Thanks to their improved data efficiency, equivariant neural networks ha...
read it

Blended Coarse Gradient Descent for Full Quantization of Deep Neural Networks
Quantized deep neural networks (QDNNs) are attractive due to their much ...
read it

Relaxed Quantization for Discretized Neural Networks
Neural network quantization has become an important research area due to...
read it

DataFree Quantization through Weight Equalization and Bias Correction
We introduce a datafree quantization method for deep neural networks th...
read it

Improving performance of recurrent neural network with relu nonlinearity
In recent years significant progress has been made in successfully train...
read it

Summarized Network Behavior Prediction
This work studies the entitywise topical behavior from massive network ...
read it

A NonBinary Associative Memory with Exponential Pattern Retrieval Capacity and Iterative Learning: Extended Results
We consider the problem of neural association for a network of nonbinar...
read it

Efficient L1Norm PrincipalComponent Analysis via Bit Flipping
It was shown recently that the K L1norm principal components (L1PCs) o...
read it

A Novel Stochastic Decoding of LDPC Codes with Quantitative Guarantees
Lowdensity paritycheck codes, a class of capacityapproaching linear c...
read it

Liquid Cloud Storage
A liquid system provides durable object storage based on spreading redun...
read it

Can Negligible Cooperation Increase Network Capacity? The AverageError Case
In communication networks, cooperative strategies are coding schemes whe...
read it

Secrecy Capacity of Colored Gaussian Noise Channels with Feedback
In this paper, the kth order autoregressive moving average (ARMA(k)) Ga...
read it

The Birthday Problem and ZeroError List Codes
As an attempt to bridge the gap between classical information theory and...
read it

Simultaneous Traffic Sign Detection and Boundary Estimation using Convolutional Neural Network
We propose a novel traffic sign detection system that simultaneously est...
read it

A QuantizationFriendly Separable Convolution for MobileNets
As deep learning (DL) is being rapidly pushed to edge computing, researc...
read it

GANAX: A Unified MIMDSIMD Acceleration for Generative Adversarial Networks
Generative Adversarial Networks (GANs) are one of the most recent deep l...
read it

Beamforming in Millimeter Wave Systems: Prototyping and Measurement Results
Demonstrating the feasibility of large antenna array beamforming is esse...
read it

Uplink Massive MIMO for Channels with Spatial Correlation
A massive MIMO system entails a large number of base station antennas M ...
read it

On the Fundamental Limits of MIMO Massive Multiple Access Channels
In this paper, we study multipleantenna wireless communication networks...
read it

Fast Onthefly Retrainingfree Sparsification of Convolutional Neural Networks
Modern Convolutional Neural Networks (CNNs) are complex, encompassing mi...
read it

MIMO Channel Information Feedback Using Deep Recurrent Network
In a multipleinput multipleoutput (MIMO) system, the availability of c...
read it

Trained Rank Pruning for Efficient Deep Neural Networks
The performance of Deep Neural Networks (DNNs) keeps elevating in recent...
read it

DAC: Datafree Automatic Acceleration of Convolutional Networks
Deploying a deep learning model on mobile/IoT devices is a challenging t...
read it

Evolution of PhysicalLayer Communications Research in the Post5G Era
The evolving Fifth Generation New Radio (5GNR) cellular standardization...
read it

Secure Massive MIMO Communication with Lowresolution DACs
In this paper, we investigate secure transmission in a massive multiple...
read it

Simulating Execution Time of Tensor Programs using Graph Neural Networks
Optimizing the execution time of tensor program, e.g., a convolution, in...
read it

HarvestorTransmit Policy for Cognitive Radio Networks: A Learning Theoretic Approach
We consider an underlay cognitive radio network where the secondary user...
read it

MixedSignal ChargeDomain Acceleration of Deep Neural networks through Interleaved BitPartitioned Arithmetic
Lowpower potential of mixedsignal design makes it an alluring option t...
read it

An EndtoEnd Textindependent Speaker Verification Framework with a Keyword Adversarial Network
This paper presents an endtoend textindependent speaker verification ...
read it

Demand Private Coded Caching
The work by MaddahAli and Niesen demonstrated the benefits in reducing ...
read it

Traned Rank Pruning for Efficient Deep Neural Networks
To accelerate DNNs inference, lowrank approximation has been widely ado...
read it

DemandPrivate Coded Caching and the Exact Tradeoff for N=K=2
The distributed coded caching problem has been studied extensively in th...
read it

FineGrained Neural Architecture Search
We present an elegant framework of finegrained neural architecture sear...
read it

Negligible Cooperation: Contrasting the Maximal and AverageError Cases
In communication networks, cooperative strategies are coding schemes whe...
read it

QKD: Quantizationaware Knowledge Distillation
Quantization and Knowledge distillation (KD) methods are widely used to ...
read it

SIFO: Secure Computational Infrastructure using FPGA Overlays
Secure Function Evaluation (SFE) has received recent attention due to th...
read it

ℓ_0 Regularized Structured Sparsity Convolutional Neural Networks
Deepening and widening convolutional neural networks (CNNs) significantl...
read it

Coded Federated Learning
Federated learning is a method of training a global model from decentral...
read it
Qualcomm
Qualcomm Incorporated is an American multinational semiconductor and telecommunications equipment company that designs and markets wireless telecommunications products and services.