Deep Graph Neural Networks (GNNs) show promising performance on a range of graph tasks, yet at present are costly to run and lack many of the optimisations applied to DNNs. We show, for the first time, how to systematically quantise GNNs with minimal or no loss in performance using Network Architecture Search (NAS). We define the possible quantisation search space of GNNs. The proposed novel NAS mechanism, named Low Precision Graph NAS (LPGNAS), constrains both architecture and quantisation choices to be differentiable. LPGNAS learns the optimal architecture coupled with the best quantisation strategy for different components in the GNN automatically using back-propagation in a single search round. On eight different datasets, solving the task of classifying unseen nodes in a graph, LPGNAS generates quantised models with significant reductions in both model and buffer sizes but with similar accuracy to manually designed networks and other NAS results. In particular, on the Pubmed dataset, LPGNAS shows a better size-accuracy Pareto frontier compared to seven other manual and searched baselines, offering a 2.3 times reduction in model size but a 0.4% increase in accuracy when compared to the best NAS competitor. Finally, from our collected quantisation statistics on a wide range of datasets, we suggest a W4A8 (4-bit weights, 8-bit activations) quantisation strategy might be the bottleneck for naive GNN quantisations.
Well-trained generative neural networks (GNN) are very efficient at compressing visual information for static images in their learned parameters but not as efficient as inter- and intra-prediction for most video content. However, for content entering a frame, such as during panning or zooming out, and content with curves, irregular shapes, or fine detail, generation by a GNN can give better compression efficiency (lower rate-distortion). This paper proposes encoding content-specific learned parameters of a GNN within a video bitstream at specific times and using the GNN to generate content for…
Deep networks run with low precision operations at inference time offer power and space advantages over high precision alternatives, but need to overcome the challenge of maintaining high accuracy as precision decreases. Here, we present a method for training such networks, Learned Step Size Quantization, that achieves the highest accuracy to date on the ImageNet dataset when using models, from a variety of architectures, with weights and activations quantized to 2-, 3- or 4-bits of precision, and that can train 3-bit models that reach full precision baseline accuracy. Our approach builds upon…
Stripes is a Deep Neural Network (DNN) accelerator that uses bit-serial computation to offer performance that is proportional to the fixed-point precision of the activation values. The fixed-point precisions are determined a priori using profiling and are selected at a per layer granularity. This paper presents Dynamic Stripes, an extension to Stripes that detects precision variance at runtime and at a finer granularity. This extra level of precision reduction increases performance by 41% over Stripes.
Dipartimento di Matematica e Informatica（数学与信息学系）；Universitá degli Studi di Palermo（巴勒莫大学）
With the aim of obtaining time/space improvements in classic Data Structures, an emerging trend is to combine Machine Learning techniques with the ones proper of Data Structures. This new area goes under the name of Learned Data Structures. The motivation for its study is a perceived change of paradigm in Computer Architectures that would favour the use of Graphics Processing Units and Tensor Processing Units over conventional Central Processing Units. In turn, that would favour the use of Neural Networks as building blocks of Classic Data Structures. Indeed, Learned Bloom Filters, which are o…
University of Toronto（多伦多大学）；University of British Columbia（不列颠哥伦比亚大学）
This work investigates how using reduced precision data in Convolutional Neural Networks (CNNs) affects network accuracy during classification. More specifically, this study considers networks where each layer may use different precision data. Our key result is the observation that the tolerance of CNNs to reduced precision data not only varies across networks, a well established observation, but also within networks. Tuning precision per layer is appealing as it could enable energy and performance improvements. In this paper we study how error tolerance across layers varies and propose a meth…
Cornell University（康奈尔大学）；University of Wyoming（怀俄明大学）；Columbia University（哥伦比亚大学）
Recent success in training deep neural networks have prompted active investigation into the features learned on their intermediate layers. Such research is difficult because it requires making sense of non-linear computations performed by millions of parameters, but valuable because it increases our ability to understand current models and create improved versions of them. In this paper we investigate the extent to which neural networks exhibit what we call convergent learning, which is when the representations learned by multiple nets converge to a set of features which are either individuall…
Low-precision formats have proven to be an efficient way to reduce not only the memory footprint but also the hardware resources and power consumption of deep learning computations. Under this premise, the posit numerical format appears to be a highly viable substitute for the IEEE floating-point, but its application to neural networks training still requires further research. Some preliminary results have shown that 8-bit (and even smaller) posits may be used for inference and 16-bit for training, while maintaining the model accuracy. The presented research aims to evaluate the feasibility to…
Institute of Technologies and Management of Digital Transformation（数字化转型技术与管理研究所）；Institute of Information Management in Mechanical Engineering（机械工程信息管理研究所）
The need for more transparency of the decision-making processes in artificial neural networks steadily increases driven by their applications in safety critical and ethically challenging domains such as autonomous driving or medical diagnostics. We address today's lack of transparency of neural networks and shed light on the roles of single neurons and groups of neurons within the network fulfilling a learned task. Inspired by research in the field of neuroscience, we characterize the learned representations by activation patterns and network ablations, revealing functional neuron populations …
A key to deciphering the inner workings of neural networks is understanding what a model has learned. Promising methods for discovering learned features are based on analyzing activation values, whereby current techniques focus on analyzing high activation values to reveal interesting features on a neuron level. However, analyzing high activation values limits layer-level concept discovery. We present a method that instead takes into account the entire activation distribution. By extracting similar activation profiles within the high-dimensional activation space of a neural network layer, we f…
Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Jilin University（吉林大学）
Accelerating deep convolutional neural networks has become an active topic and sparked an interest in academia and industry. In this paper, we propose an efficient low-precision quantized Winograd convolution algorithm, called LANCE, which combines the advantages of fast convolution and quantization techniques. By embedding linear quantization operations into the Winograd-domain, the fast convolution can be performed efficiently under low-precision computation on graphics processing units. We test neural network models with LANCE on representative image classification datasets, including SVHN,…
Université de Toulouse（图卢兹大学）；CNRS（法国国家科学研究中心）；UPS（图卢兹第三大学）
We explore the influence of precision of the data and the algorithm for the simulation of chaotic dynamics by neural networks techniques. For this purpose, we simulate the Lorenz system with different precisions using three different neural network techniques adapted to time series, namely reservoir computing (using ESN), LSTM and TCN, for both short and long time predictions, and assess their efficiency and accuracy. Our results show that the ESN network is better at predicting accurately the dynamics of the system, and that in all cases the precision of the algorithm is more important than t…
École Polytechnique de Montréal（蒙特利尔综合理工学院）；Université de Montréal（蒙特利尔大学）
Multipliers are the most space and power-hungry arithmetic operators of the digital implementation of deep neural networks. We train a set of state-of-the-art neural networks (Maxout networks) on three benchmark datasets: MNIST, CIFAR-10 and SVHN. They are trained with three distinct formats: floating point, fixed point and dynamic fixed point. For each of those datasets and for each of those formats, we assess the impact of the precision of the multiplications on the final error after training. We find that very low precision is sufficient not just for running trained networks but also for tr…
We consider learning deep neural networks (DNNs) that consist of low-precision weights and activations for efficient inference of fixed-point operations. In training low-precision networks, gradient descent in the backward pass is performed with high-precision weights while quantized low-precision weights and activations are used in the forward pass to calculate the loss function for training. Thus, the gradient descent becomes suboptimal, and accuracy loss follows. In order to reduce the mismatch in the forward and backward passes, we utilize mean squared quantization error (MSQE) regularizat…
We explore neural painters, a generative model for brushstrokes learned from a real non-differentiable and non-deterministic painting program. We show that when training an agent to "paint" images using brushstrokes, using a differentiable neural painter leads to much faster convergence. We propose a method for encouraging this agent to follow human-like strokes when reconstructing digits. We also explore the use of a neural painter as a differentiable image parameterization. By directly optimizing brushstrokes to activate neurons in a pre-trained convolutional network, we can directly visuali…
To compare entities of differing types and structural components, the artificial neural network paradigm was used to cross-compare structural components between heterogeneous documents. Trainable weighted structural components were input into machine-learned activation functions of the neurons. The model was used for matching news articles and videos, where the inputs and activation functions respectively consisted of term vectors and cosine similarity measures between the weighted structural components. The model was tested with different weights, achieving as high as 59.2% accuracy for match…
In this paper, we propose a novel learning based method for automated segmenta-tion of brain tumor in multimodal MRI images. The machine learned features from fully convolutional neural network (FCN) and hand-designed texton fea-tures are used to classify the MRI image voxels. The score map with pixel-wise predictions is used as a feature map which is learned from multimodal MRI train-ing dataset using the FCN. The learned features are then applied to random for-ests to classify each MRI image voxel into normal brain tissues and different parts of tumor. The method was evaluated on BRATS 2013 …
Conventional stochastic rounding (CSR) is widely employed in the training of neural networks (NNs), showing promising training results even in low-precision computations. We introduce an improved stochastic rounding method, that is simple and efficient. The proposed method succeeds in training NNs with 16-bit fixed-point numbers and provides faster convergence and higher classification accuracy than both CSR and deterministic rounding-to-the-nearest method.
We show that the error achievable using physics-informed neural networks for solving systems of differential equations can be substantially reduced when these networks are trained using meta-learned optimization methods rather than to using fixed, hand-crafted optimizers as traditionally done. We choose a learnable optimization method based on a shallow multi-layer perceptron that is meta-trained for specific classes of differential equations. We illustrate meta-trained optimizers for several equations of practical relevance in mathematical physics, including the linear advection equation, Poi…
Beyond the generally deployed features for microstructure property prediction this study aims to improve the machine learned prediction by developing novel feature descriptors. Therefore, Bayesian infused data mining is conducted to acquire samples containing characteristics inexplicable to the current feature set, and suitable feature descriptors to describe these characteristics are proposed. The iterative development of feature descriptors resulted in 37 novel features, being able to reduce the prediction error by roughly one third. To further improve the predictive model, convolutional neu…
NVIDIA（英伟达）；University of Guelph（圭尔夫大学）；Vector Institute for Artificial Intelligence（向量人工智能研究所）；Canadian Institute for Advanced Research（加拿大高等研究院）
Low precision weights, activations, and gradients have been proposed as a way to improve the computational efficiency and memory footprint of deep neural networks. Recently, low precision networks have even shown to be more robust to adversarial attacks. However, typical implementations of low precision DNNs use uniform precision across all layers of the network. In this work, we explore whether a heterogeneous allocation of precision across a network leads to improved performance, and introduce a learning scheme where a DNN stochastically explores multiple precision configurations through lea…
A key contributing factor to incredible success of deep neural networks has been the significant rise on massively parallel computing devices allowing researchers to greatly increase the size and depth of deep neural networks, leading to significant improvements in modeling accuracy. Although deeper, larger, or complex deep neural networks have shown considerable promise, the computational complexity of such networks is a major barrier to utilization in resource-starved scenarios. We explore the synaptogenesis of deep neural networks in the formation of efficient deep neural network architectu…
Low-precision networks, with weights and activations quantized to low bit-width, are widely used to accelerate inference on edge devices. However, current solutions are uniform, using identical bit-width for all filters. This fails to account for the different sensitivities of different filters and is suboptimal. Mixed-precision networks address this problem, by tuning the bit-width to individual filter requirements. In this work, the problem of optimal mixed-precision network search (MPS) is considered. To circumvent its difficulties of discrete search space and combinatorial optimization, a …
Seismic monitoring of carbon storage sequestration is a challenging problem involving both fluid-flow physics and wave physics. Additionally, monitoring usually requires the solvers for these physics to be coupled and differentiable to effectively invert for the subsurface properties of interest. To drastically reduce the computational cost, we introduce a learned coupled inversion framework based on the wave modeling operator, rock property conversion and a proxy fluid-flow simulator. We show that we can accurately use a Fourier neural operator as a proxy for the fluid-flow simulator for a fr…
The `Internet of Things' has brought increased demand for AI-based edge computing in applications ranging from healthcare monitoring systems to autonomous vehicles. Quantization is a powerful tool to address the growing computational cost of such applications, and yields significant compression over full-precision networks. However, quantization can result in substantial loss of performance for complex image classification tasks. To address this, we propose a Principal Component Analysis (PCA) driven methodology to identify the important layers of a binary network, and design mixed-precision n…
Institute for Human Genetics（人类遗传学研究所）；University of California, San Francisco（加州大学旧金山分校）；Enlitic（Enlitic公司）
Each human genome is a 3 billion base pair set of encoding instructions. Decoding the genome using deep learning fundamentally differs from most tasks, as we do not know the full structure of the data and therefore cannot design architectures to suit it. As such, architectures that fit the structure of genomics should be learned not prescribed. Here, we develop a novel search algorithm, applicable across domains, that discovers an optimal architecture which simultaneously learns general genomic patterns and identifies the most important sequence motifs in predicting functional genomic outcomes…
Tsinghua University（清华大学）；Peng Cheng Laboratory（鹏城实验室）；Shanghai Jiao Tong University（上海交通大学）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）
The exponentially large discrete search space in mixed-precision quantization (MPQ) makes it hard to determine the optimal bit-width for each layer. Previous works usually resort to iterative search methods on the training set, which consume hundreds or even thousands of GPU-hours. In this study, we reveal that some unique learnable parameters in quantization, namely the scale factors in the quantizer, can serve as importance indicators of a layer, reflecting the contribution of that layer to the final accuracy at certain bit-widths. These importance indicators naturally perceive the numerical…
Universiteit van Amsterdam（阿姆斯特丹大学）；Tilburg University（蒂尔堡大学）；German Center for AI (DFKI)（德国人工智能研究中心）
Two popular types of machine translation (MT) are phrase-based and neural machine translation systems. Both of these types of systems are composed of multiple complex models or layers. Each of these models and layers learns different linguistic aspects of the source language. However, for some of these models and layers, it is not clear which linguistic phenomena are learned or how this information is learned. For phrase-based MT systems, it is often clear what information is learned by each model, and the question is rather how this information is learned, especially for its phrase reordering…
Department of Electrical and Computer Engineering（电气与计算机工程系）；University of Toronto（多伦多大学）；Toronto, ON, Canada（加拿大安大略省多伦多市）
Recent work has explored reduced numerical precision for parameters, activations, and gradients during neural network training as a way to reduce the computational cost of training (Na & Mukhopadhyay, 2016) (Courbariaux et al., 2014). We present a novel dynamic precision scaling (DPS) scheme. Using stochastic fixed-point rounding, a quantization-error based scaling scheme, and dynamic bit-widths during training, we achieve 98.8% test accuracy on the MNIST dataset using an average bit-width of just 16 bits for weights and 14 bits for activations, compared to the standard 32-bit floating point v…
Multi-task neural networks by learned contextual inputs
Solution Seeker AS（Solution Seeker公司）；University of Oslo（奥斯陆大学）；Norwegian University of Science and Technology（挪威科技大学）；Department of Mathematics（数学系）；Department of Engineering Cybernetics（工程控制系）
In this paper, we evaluate training of deep recurrent neural networks with half-precision floats. We implement a distributed, data-parallel, synchronous training algorithm by integrating TensorFlow and CUDA-aware MPI to enable execution across multiple GPU nodes and making use of high-speed interconnects. We introduce a learning rate schedule facilitating neural network convergence at up to $O(100)$ workers. Strong scaling tests performed on clusters of NVIDIA Pascal P100 GPUs show linear runtime and logarithmic communication time scaling for both single and mixed precision training modes. Per…
Large-scale deep neural networks (DNN) have been successfully used in a number of tasks from image recognition to natural language processing. They are trained using large training sets on large models, making them computationally and memory intensive. As such, there is much interest in research development for faster training and test time. In this paper, we present a unique approach using lower precision weights for more efficient and faster training phase. We separate imagery into different frequency bands (e.g. with different information content) such that the neural net can better learn u…
Adaptive Precision Training: Quantify Back Propagation in Neural Networks with Fixed-point Numbers. Recent emerged quantization technique has been applied to inference of deep neural networks for fast and efficient execution. However, directly applying quantization in training can cause significant accuracy loss, thus remaining an open challenge.
Symmetries built into a neural network have appeared to be very beneficial for a wide range of tasks as it saves the data to learn them. We depart from the position that when symmetries are not built into a model a priori, it is advantageous for robust networks to learn symmetries directly from the data to fit a task function. In this paper, we present a method to extract symmetries learned by a neural network and to evaluate the degree to which a network is invariant to them. With our method, we are able to explicitly retrieve learned invariances in a form of the generators of corresponding L…
Neural CDEs as Correctors for Learned Time Series Models
Department of Mechanical Engineering（机械工程系）；Iowa State University（爱荷华州立大学）；Sibley School of Mechanical and Aerospace Engineering（机械与航空航天工程学院）；Cornell University（康奈尔大学）
Institute of Computer Science, University of St.Gallen (HSG)（圣加仑大学（HSG）计算机科学研究所）
The commitment to single-precision floating-point arithmetic is widespread in the deep learning community. To evaluate whether this commitment is justified, the influence of computing precision (single and double precision) on the optimization performance of the Conjugate Gradient (CG) method (a second-order optimization algorithm) and RMSprop (a first-order algorithm) has been investigated. Tests of neural networks with one to five fully connected hidden layers and moderate or strong nonlinearity with up to 4 million network parameters have been optimized for Mean Square Error (MSE). The trai…
We study the ability of foundation models to learn representations for classification that are transferable to new, unseen classes. Recent results in the literature show that representations learned by a single classifier over many classes are competitive on few-shot learning problems with representations learned by special-purpose algorithms designed for such problems. In this paper we provide an explanation for this behavior based on the recently observed phenomenon that the features learned by overparameterized classification networks show an interesting clustering property, called neural c…
In this paper, we present Neural-Swarm, a nonlinear decentralized stable controller for close-proximity flight of multirotor swarms. Close-proximity control is challenging due to the complex aerodynamic interaction effects between multirotors, such as downwash from higher vehicles to lower ones. Conventional methods often fail to properly capture these interaction effects, resulting in controllers that must maintain large safety distances between vehicles, and thus are not capable of close-proximity flight. Our approach combines a nominal dynamics model with a regularized permutation-invariant…
Stanford University（斯坦福大学）；Intel AI Lab（英特尔人工智能实验室）
Training with larger number of parameters while keeping fast iterations is an increasingly adopted strategy and trend for developing better performing Deep Neural Network (DNN) models. This necessitates increased memory footprint and computational requirements for training. Here we introduce a novel methodology for training deep neural networks using 8-bit floating point (FP8) numbers. Reduced bit precision allows for a larger effective memory and increased computational speed. We name this method Shifted and Squeezed FP8 (S2FP8). We show that, unlike previous 8-bit precision training methods,…
We present PrecisionBatching, a quantized inference algorithm for speeding up neural network execution on traditional hardware platforms at low bitwidths without the need for retraining or recalibration. PrecisionBatching decomposes a neural network into individual bitlayers and accumulates them using fast 1-bit operations while maintaining activations in full precision. PrecisionBatching not only facilitates quantized inference at low bitwidths (< 8 bits) without the need for retraining/recalibration, but also 1) enables traditional hardware platforms the ability to realize inference speedups…
We propose precision gating (PG), an end-to-end trainable dynamic dual-precision quantization technique for deep neural networks. PG computes most features in a low precision and only a small proportion of important features in a higher precision to preserve accuracy. The proposed approach is applicable to a variety of DNN architectures and significantly reduces the computational cost of DNN execution with almost no accuracy loss. Our experiments indicate that PG achieves excellent results on CNNs, including statically compressed mobile-friendly networks such as ShuffleNet. Compared to the sta…
Indian Institute of Technology Hyderabad（印度理工学院海得拉巴分校）；Microsoft Research（微软研究院）
A trained neural network can be interpreted as a structural causal model (SCM) that provides the effect of changing input variables on the model's output. However, if training data contains both causal and correlational relationships, a model that optimizes prediction accuracy may not necessarily learn the true causal relationships between input and output variables. On the other hand, expert users often have prior knowledge of the causal relationship between certain input variables and output from domain knowledge. Therefore, we propose a regularization method that aligns the learned causal e…
Forschungszentrum Jülich（于利希研究中心）；University of Cologne（科隆大学）；Helmholtz AI（亥姆霍兹人工智能）
To test generalization ability of a class of deep neural networks, we randomly generate a large number of different rule sets for 2-D cellular automata (CA), based on John Conway's Game of Life. Using these rules, we compute several trajectories for each CA instance. A deep convolutional encoder-decoder network with short and long range skip connections is trained on various generated CA trajectories to predict the next CA state given its previous states. Results show that the network is able to learn the rules of various, complex cellular automata and generalize to unseen configurations. To s…
We present Neural-Swarm2, a learning-based method for motion planning and control that allows heterogeneous multirotors in a swarm to safely fly in close proximity. Such operation for drones is challenging due to complex aerodynamic interaction forces, such as downwash generated by nearby drones and ground effect. Conventional planning and control methods neglect capturing these interaction forces, resulting in sparse swarm configuration during flight. Our approach combines a physics-based nominal dynamics model with learned Deep Neural Networks (DNNs) with strong Lipschitz properties. We make…
