AIgean : An Open Framework for Deploying Machine Learning on Heterogeneous Clusters

2022 ◽  
Vol 15 (3) ◽  
pp. 1-32
Author(s):  
Naif Tarafdar ◽  
Giuseppe Di Guglielmo ◽  
Philip C. Harris ◽  
Jeffrey D. Krupa ◽  
Vladimir Loncar ◽  
...  

  AIgean , pronounced like the sea, is an open framework to build and deploy machine learning (ML) algorithms on a heterogeneous cluster of devices (CPUs and FPGAs). We leverage two open source projects: Galapagos , for multi-FPGA deployment, and hls4ml , for generating ML kernels synthesizable using Vivado HLS. AIgean provides a full end-to-end multi-FPGA/CPU implementation of a neural network. The user supplies a high-level neural network description, and our tool flow is responsible for the synthesizing of the individual layers, partitioning layers across different nodes, as well as the bridging and routing required for these layers to communicate. If the user is an expert in a particular domain and would like to tinker with the implementation details of the neural network, we define a flexible implementation stack for ML that includes the layers of Algorithms, Cluster Deployment & Communication, and Hardware. This allows the user to modify specific layers of abstraction without having to worry about components outside of their area of expertise, highlighting the modularity of AIgean . We demonstrate the effectiveness of AIgean with two use cases: an autoencoder, and ResNet-50 running across 10 and 12 FPGAs. AIgean leverages the FPGA’s strength in low-latency computing, as our implementations target batch-1 implementations.

2019 ◽  
Vol 488 (2) ◽  
pp. 2263-2274
Author(s):  
Bhavana D. ◽  
S Vig ◽  
S K Ghosh ◽  
Rama Krishna Sai S Gorthi

ABSTRACT The application of machine learning principles in the photometric search of elusive astronomical objects has been a less-explored frontier of research. Here, we have used three methods, the neural network and two variants of k-nearest neighbour, to identify brown dwarf candidates using the photometric colours of known brown dwarfs. We initially check the efficiencies of these three classification techniques, both individually and collectively, on known objects. This is followed by their application to three regions in the sky, namely Hercules (2° × 2°), Serpens (9° × 4°), and Lyra (2° × 2°). Testing these algorithms on sets of objects that include known brown dwarfs show a high level of completeness. This includes the Hercules and Serpens regions where brown dwarfs have been detected. We use these methods to search and identify brown dwarf candidates towards the Lyra region. We infer that the collective method of classification, also known as ensemble classifier, is highly efficient in the identification of brown dwarf candidates.


2021 ◽  
pp. FSO698
Author(s):  
Aravind Akella ◽  
Sudheer Akella

Aim: The development of coronary artery disease (CAD), a highly prevalent disease worldwide, is influenced by several modifiable risk factors. Predictive models built using machine learning (ML) algorithms may assist clinicians in timely detection of CAD and may improve outcomes. Materials & methods: In this study, we applied six different ML algorithms to predict the presence of CAD amongst patients listed in ‘the Cleveland dataset.’ The generated computer code is provided as a working open source solution with the ultimate goal to achieve a viable clinical tool for CAD detection. Results: All six ML algorithms achieved accuracies greater than 80%, with the ‘neural network’ algorithm achieving accuracy greater than 93%. The recall achieved with the ‘neural network’ model is also the highest of the six models (0.93), indicating that predictive ML models may provide diagnostic value in CAD.


2021 ◽  
Vol 0 (0) ◽  
Author(s):  
Idris Kharroubi ◽  
Thomas Lim ◽  
Xavier Warin

AbstractWe study the approximation of backward stochastic differential equations (BSDEs for short) with a constraint on the gains process. We first discretize the constraint by applying a so-called facelift operator at times of a grid. We show that this discretely constrained BSDE converges to the continuously constrained one as the mesh grid converges to zero. We then focus on the approximation of the discretely constrained BSDE. For that we adopt a machine learning approach. We show that the facelift can be approximated by an optimization problem over a class of neural networks under constraints on the neural network and its derivative. We then derive an algorithm converging to the discretely constrained BSDE as the number of neurons goes to infinity. We end by numerical experiments.


Electronics ◽  
2020 ◽  
Vol 10 (1) ◽  
pp. 52
Author(s):  
Richard Evan Sutanto ◽  
Sukho Lee

Several recent studies have shown that artificial intelligence (AI) systems can malfunction due to intentionally manipulated data coming through normal channels. Such kinds of manipulated data are called adversarial examples. Adversarial examples can pose a major threat to an AI-led society when an attacker uses them as means to attack an AI system, which is called an adversarial attack. Therefore, major IT companies such as Google are now studying ways to build AI systems which are robust against adversarial attacks by developing effective defense methods. However, one of the reasons why it is difficult to establish an effective defense system is due to the fact that it is difficult to know in advance what kind of adversarial attack method the opponent is using. Therefore, in this paper, we propose a method to detect the adversarial noise without knowledge of the kind of adversarial noise used by the attacker. For this end, we propose a blurring network that is trained only with normal images and also use it as an initial condition of the Deep Image Prior (DIP) network. This is in contrast to other neural network based detection methods, which require the use of many adversarial noisy images for the training of the neural network. Experimental results indicate the validity of the proposed method.


Mining ◽  
2021 ◽  
Vol 1 (3) ◽  
pp. 279-296
Author(s):  
Marc Elmouttie ◽  
Jane Hodgkinson ◽  
Peter Dean

Geotechnical complexity in mining often leads to geotechnical uncertainty which impacts both safety and productivity. However, as mining progresses, particularly for strip mining operations, a body of knowledge is acquired which reduces this uncertainty and can potentially be used by mining engineers to improve the prediction of future mining conditions. In this paper, we describe a new method to support this approach based on modelling and neural networks. A high-level causal model of the mining operations based on historical data for a number of parameters was constructed which accounted for parameter interactions, including hydrogeological conditions, weather, and prior operations. An artificial neural network was then trained on this historical data, including production data. The network can then be used to predict future production based on presently observed mining conditions as mining proceeds and compared with the model predictions. Agreement with the predictions indicates confidence that the neural network predictions are properly supported by the newly available data. The efficacy of this approach is demonstrated using semi-synthetic data based on an actual mine.


2020 ◽  
Vol 73 (7) ◽  
pp. 1499-1504
Author(s):  
Oleksandr A. Udod ◽  
Hanna S. Voronina ◽  
Olena Yu. Ivchenkova

The aim: of the work was to develop and apply in the clinical trial a software product for the dental caries prediction based on neural network programming. Materials and methods: Dental examination of 73 persons aged 6-7, 12-15 and 35-44 years was carried out. The data obtained during the survey were used as input for the construction and training of the neural network. The output index was determined by the increase in the intensity of caries, taking into account the number of cavities. To build a neural network, a high-level Python programming language with the NumPay extension was used. Results: The intensity of carious dental lesions was the highest in 35-44 years old patients – 6.69 ± 0.38, in 6-7 years old children and 12-15 years old children it was 3.85 ± 0.27 and 2.15 ± 0.24, respectively (p <0.05). After constructing and training the neural network, 61 true and 12 false predictions were obtained based on these indices, the accuracy of predicting the occurrence of caries was 83.56%. Based on these results, a graphical user interface for the “CariesPro” software application was created. Conclusions: The resulting neural network and the software product based on it permit to predict the development of dental caries in persons of all ages with a probability of 83.56%.


Terminology ◽  
2022 ◽  
Author(s):  
Ayla Rigouts Terryn ◽  
Véronique Hoste ◽  
Els Lefever

Abstract As with many tasks in natural language processing, automatic term extraction (ATE) is increasingly approached as a machine learning problem. So far, most machine learning approaches to ATE broadly follow the traditional hybrid methodology, by first extracting a list of unique candidate terms, and classifying these candidates based on the predicted probability that they are valid terms. However, with the rise of neural networks and word embeddings, the next development in ATE might be towards sequential approaches, i.e., classifying each occurrence of each token within its original context. To test the validity of such approaches for ATE, two sequential methodologies were developed, evaluated, and compared: one feature-based conditional random fields classifier and one embedding-based recurrent neural network. An additional comparison was added with a machine learning interpretation of the traditional approach. All systems were trained and evaluated on identical data in multiple languages and domains to identify their respective strengths and weaknesses. The sequential methodologies were proven to be valid approaches to ATE, and the neural network even outperformed the more traditional approach. Interestingly, a combination of multiple approaches can outperform all of them separately, showing new ways to push the state-of-the-art in ATE.


2021 ◽  
Vol 105 ◽  
pp. 241-248
Author(s):  
Abhishek Choubey ◽  
Shruti Bhargava Choubey

Recent neural network research has demonstrated a significant benefit in machine learning compared to conventional algorithms based on handcrafted models and features. In regions such as video, speech and image recognition, the neural network is now widely adopted. But the high complexity of neural network inference in computation and storage poses great differences on its application. These networks are computer-intensive algorithms that currently require the execution of dedicated hardware. In this case, we point out the difficulty of Adders (MOAs) and their high-resource utilization in a CNN implementation of FPGA .to address these challenge a parallel self-time adder is implemented which mainly aims at minimizing the amount of transistors and estimating different factors for PASTA, i.e. field, power, delay.


Geophysics ◽  
2020 ◽  
Vol 85 (4) ◽  
pp. WA41-WA52 ◽  
Author(s):  
Dario Grana ◽  
Leonardo Azevedo ◽  
Mingliang Liu

Among the large variety of mathematical and computational methods for estimating reservoir properties such as facies and petrophysical variables from geophysical data, deep machine-learning algorithms have gained significant popularity for their ability to obtain accurate solutions for geophysical inverse problems in which the physical models are partially unknown. Solutions of classification and inversion problems are generally not unique, and uncertainty quantification studies are required to quantify the uncertainty in the model predictions and determine the precision of the results. Probabilistic methods, such as Monte Carlo approaches, provide a reliable approach for capturing the variability of the set of possible models that match the measured data. Here, we focused on the classification of facies from seismic data and benchmarked the performance of three different algorithms: recurrent neural network, Monte Carlo acceptance/rejection sampling, and Markov chain Monte Carlo. We tested and validated these approaches at the well locations by comparing classification predictions to the reference facies profile. The accuracy of the classification results is defined as the mismatch between the predictions and the log facies profile. Our study found that when the training data set of the neural network is large enough and the prior information about the transition probabilities of the facies in the Monte Carlo approach is not informative, machine-learning methods lead to more accurate solutions; however, the uncertainty of the solution might be underestimated. When some prior knowledge of the facies model is available, for example, from nearby wells, Monte Carlo methods provide solutions with similar accuracy to the neural network and allow a more robust quantification of the uncertainty, of the solution.


Author(s):  
Zihao Zhang ◽  
Junkang Guo ◽  
Yanhui Sun ◽  
Jun Hong

Abstract The eccentricity of rotor seriously affect the vibration and reliability of aero-engine. Due to the machining error of parts, it is very important to accurately predict the error propagation in assembly. A method based on image recognition and machine learning is proposed to predict the eccentricity of rotor. Firstly, by analyzing and calculating the axial and radial runout error data, the error is mainly concentrated in the first 30 orders of the Fourier series. Secondly, based on the mapping relationship between profile trajectory and eccentricity of rotor, the feature information of the profile trajectory is extracted by constructing the complex domain autoregressive (CAR) model for the radial and axial direction error profile trajectory. Then use the finite element method to calculate the rotor eccentricity. Using the feature information as the input of the neural network, the rotor eccentricity is assembled as the output of the neural network, and the radial basis function (RBF) neural network is built to predict the rotor eccentricity. Theoretical and experimental results show that the proposed method has good enforceability, high accuracy, short calculation time and high engineering application value. In addition, this method can not only be applied to predict the eccentricity of aero-engine rotor flange assembly, but also can be used in the general field of interference fit of assembly.


Sign in / Sign up

Export Citation Format

Share Document