Related papers: TreeLUT: An Efficient Alternative to Deep Neural N…

Recently proposed Gated Linear Networks present a tractable nonlinear network architecture, and exhibit interesting capabilities such as learning with local error signals and reduced forgetting in sequential learning. In this work, we…

The conventional LUT is redundant since practical functions in real-world benchmarks only occupy a small proportion of all the functions. For example, there are only 3881 out of more than $10^{14}$ NPN classes of 6-input functions occurring…

Neural networks (NNs) and decision trees (DTs) are both popular models of machine learning, yet coming with mutually exclusive advantages and limitations. To bring the best of the two worlds, a variety of approaches are proposed to…

Multiplication (e.g., convolution) is arguably a cornerstone of modern deep neural networks (DNNs). However, intensive multiplications cause expensive resource costs that challenge DNNs' deployment on resource-constrained edge devices,…

In many applications of supervised learning, multiple classification or regression outputs have to be predicted jointly. We consider several extensions of gradient boosting to address such problems. We first propose a straightforward…

Deployment of deep neural networks for applications that require very high throughput or extremely low latency is a severe computational challenge, further exacerbated by inefficiencies in mapping the computation to hardware. We present a…

For classification and regression on tabular data, the dominance of gradient-boosted decision trees (GBDTs) has recently been challenged by often much slower deep learning methods with extensive hyperparameter tuning. We address this…

To overcome range anxiety problem of Electric Vehicles (EVs), an accurate real-time energy consumption estimation is necessary, which can be used to provide the EV's driver with information about the remaining range in real-time. A hybrid…

FPGA is appropriate for fix-point neural networks computing due to high power efficiency and configurability. However, its design must be intensively refined to achieve high performance using limited hardware resources. We present an…

Current state-of-the-art systems for sequence labeling are typically based on the family of Recurrent Neural Networks (RNNs). However, the shallow connections between consecutive hidden states of RNNs and insufficient modeling of global…

This paper compares the performances of three supervised machine learning algorithms in terms of predictive ability and model interpretation on structured or tabular data. The algorithms considered were scikit-learn implementations of…

Machine learning algorithms often contain many hyperparameters (HPs) whose values affect the predictive performance of the induced models in intricate ways. Due to the high number of possibilities for these HP configurations and their…

Tree based ensembles such as Breiman's random forest (RF) and Gradient Boosted Trees (GBT) can be interpreted as implicit kernel generators, where the ensuing proximity matrix represents the data-driven tree ensemble kernel. Kernel…

While GPU clusters are the de facto choice for training large deep neural network (DNN) models today, several reasons including ease of workflow, security and cost have led to efforts investigating whether CPUs may be viable for inference…

Monolithic crystals are examined as an alternative to segmented scintillator arrays in positron emission tomography (PET). Monoliths provide good energy, timing and spatial resolution including intrinsic depth of interaction (DOI) encoding.…

The exponential emergence of Field Programmable Gate Array (FPGA) has accelerated the research of hardware implementation of Deep Neural Network (DNN). Among all DNN processors, domain specific architectures, such as, Google's Tensor…

This paper presents a comprehensive review of recent advances in deploying convolutional neural networks (CNNs) for object detection, classification, and tracking on Field Programmable Gate Arrays (FPGAs). With the increasing demand for…

High quality AI solutions require joint optimization of AI algorithms and their hardware implementations. In this work, we are the first to propose a fully simultaneous, efficient differentiable DNN architecture and implementation co-search…

To improve the throughput and energy efficiency of Deep Neural Networks (DNNs) on customized hardware, lightweight neural networks constrain the weights of DNNs to be a limited combination (denoted as $k\in\{1,2\}$) of powers of 2. In such…

The rapid growth of data size and accessibility in recent years has instigated a shift of philosophy in algorithm design for artificial intelligence. Instead of engineering algorithms by hand, the ability to learn composable systems…