Search Results for author:
Found 31 papers, 8 papers with code
MGS: Markov Greedy Sums for Accurate Low-Bitwidth Floating-Point Accumulation
'swamping') is a significant source of numerical errors in accumulation when implementing low-bitwidth dot products (e. g., 8-bit floating point) as the mantissa has a small number of bits.
GazeGen: Gaze-Driven User Interaction for Visual Content Generation
GazeGen is the first system to combine visual content generation with real-time gaze estimation, made possible exclusively by DFT Gaze.
Efficient Reprogramming of Memristive Crossbars for DNNs: Weight Sorting and Bit Stucking
We introduce a novel approach to reduce the number of times required for reprogramming memristors on bit-sliced compute-in-memory crossbars for deep neural networks (DNNs).
Sorted Weight Sectioning for Energy-Efficient Unstructured Sparse DNNs on Compute-in-Memory Crossbars
SWS effectively reduces this cost leveraging (1) small weights and (2) zero weights (weight sparsity).
DeepMachining: Online Prediction of Machining Errors of Lathe Machines
Specifically, we first pretrain a deep learning model for a given lathe machine's operations to learn the salient features of machining states.
Gen4Gen: Generative Data Pipeline for Generative Multi-Concept Composition
First, current personalization techniques fail to reliably extend to multiple concepts -- we hypothesize this to be due to the mismatch between complex scenes and simple text descriptions in the pre-training dataset (e. g., LAION).
Rosko: Row Skipping Outer Products for Sparse Matrix Multiplication Kernels
We propose Rosko -- row skipping outer products -- for deriving sparse matrix multiplication (SpMM) kernels in reducing computation and memory access requirements of deep neural networks (DNNs).
MEMA Runtime Framework: Minimizing External Memory Accesses for TinyML on Microcontrollers
We present the MEMA framework for the easy and quick derivation of efficient inference runtimes that minimize external memory accesses for matrix multiplication on TinyML systems.
StitchNet: Composing Neural Networks from Pre-Trained Fragments
We then show that these fragments can be stitched together to create neural networks with accuracy comparable to that of traditionally trained networks at a fraction of computing resource and data requirements.
SpeedLimit: Neural Architecture Search for Quantized Transformer Models
While research in the field of transformer models has primarily focused on enhancing performance metrics such as accuracy and perplexity, practical applications in industry often necessitate a rigorous consideration of inference latency constraints.
SphereFed: Hyperspherical Federated Learning
Federated Learning aims at training a global model from multiple decentralized devices (i. e. clients) without exchanging their private local data.
SplitNets: Designing Neural Architectures for Efficient Distributed Computing on Head-Mounted Systems
We design deep neural networks (DNNs) and corresponding networks' splittings to distribute DNNs' workload to camera sensors and a centralized aggregator on head mounted devices to meet system performance targets in inference accuracy and latency under the given hardware resource constraints.
FAST: DNN Training Under Variable Precision Block Floating Point with Stochastic Rounding
Block Floating Point (BFP) can efficiently support quantization for Deep Neural Network (DNN) training by providing a wide dynamic range via a shared exponent across a group of values.
Privacy Vulnerability of Split Computing to Data-Free Model Inversion Attacks
Prior works usually assume that SC offers privacy benefits as only intermediate features, instead of private data, are shared from devices to the cloud.
Neural Mean Discrepancy for Efficient Out-of-Distribution Detection
Based upon this observation, we propose a novel metric called Neural Mean Discrepancy (NMD), which compares neural means of the input examples and training data.
exBERT: Extending Pre-trained Models with Domain-specific Vocabulary Under Constrained Training Resources
We introduce exBERT, a training method to extend BERT pre-trained models from a general domain to a new pre-trained model for a specific domain with a new additive vocabulary under constrained training resources (i. e., constrained computation and data).
Term Revealing: Furthering Quantization at Run Time on Quantized DNNs
To perform conversion from binary to SDR, we develop an efficient encoding method called HESE (Hybrid Encoding for Signed Expressions) that can be performed in one pass looking at only two bits at a time.
DaiMoN: A Decentralized Artificial Intelligence Model Network
A main feature of DaiMoN is that it allows peers to verify the accuracy improvement of submitted models without knowing the test labels.
Triton: An Intermediate Language and Compiler for Tiled Neural Network Computations
The validation and deployment of novel research ideas in the field of Deep Learning is often limited by the availability of efficient compute kernels for certain basic primitives.
CheckNet: Secure Inference on Untrusted Devices
CheckNet is like a checksum for neural network inference: it verifies the integrity of the inference computation performed by untrusted devices to 1) ensure the inference has actually been performed, and 2) ensure the inference has not been manipulated by an attacker.
Full-stack Optimization for Accelerating CNNs with FPGA Validation
A highlight of our full-stack approach which attributes to the achieved high energy efficiency is an efficient Selector-Accumulator (SAC) architecture for implementing the multiplier-accumulator (MAC) operation present in any digital CNN hardware.
Adversarial Learning of Semantic Relevance in Text to Image Synthesis
Instead of selecting random training examples, we perform negative sampling based on the semantic distance from a positive example in the class.
Packing Sparse Convolutional Neural Networks for Efficient Systolic Array Implementations: Column Combining Under Joint Optimization
We study the effectiveness of this joint optimization for both high utilization and classification accuracy with ASIC and FPGA designs based on efficient bit-serial implementations of multiplier-accumulators.
Incomplete Dot Products for Dynamic Computation Scaling in Neural Network Inference
At inference time, the number of channels used can be dynamically adjusted to trade off accuracy for lowered power consumption and reduced latency by selecting only a beginning subset of channels.
Embedded Binarized Neural Networks
Beyond minimizing the memory required to store weights, as in a BNN, we show that it is essential to minimize the memory used for temporaries which hold intermediate results between layers in feedforward inference.
BranchyNet: Fast Inference via Early Exiting from Deep Neural Networks
Deep neural networks are state of the art methods for many learning tasks due to their ability to extract increasingly better features at each network layer.
Distributed Deep Neural Networks over the Cloud, the Edge and End Devices
In our experiment, compared with the traditional method of offloading raw sensor data to be processed in the cloud, DDNN locally processes most sensor data on end devices while achieving high accuracy and is able to reduce the communication cost by a factor of over 20x.
Language Modeling by Clustering with Word Embeddings for Text Readability Assessment
We argue that clustering with word embeddings in the metric space should yield feature representations in a higher semantic space appropriate for text regression.
Adversarial nets with perceptual losses for text-to-image synthesis
Recent approaches in generative adversarial networks (GANs) can automatically synthesize realistic images from descriptive text.
Multimodal Sparse Coding for Event Detection
Unsupervised feature learning methods have proven effective for classification tasks based on a single modality.
Multimodal sparse representation learning and applications
In this paper, we present a multimodal framework for learning sparse representations that can capture semantic correlation between modalities.
