ANNIE: a simulated neural network for empirical studies and application prototyping

2003 ◽  
Author(s):  
W.L. Huxhold ◽  
T.F. Henson ◽  
J.D. Bowman
Keyword(s):  
Neural Network ◽  
Empirical Studies

scholarly journals Towards Better Interpretability in Deep Q-Networks

2019 ◽  
Vol 33 ◽  
pp. 4561-4569 ◽  
Author(s):  
Raghuram Mandyam Annasamy ◽  
Katia Sycara
Keyword(s):  
Neural Network ◽  
Network Architecture ◽  
Empirical Studies ◽  
Superior Performance ◽  
Training Algorithms ◽  
Neural Network Architecture ◽  
Q Learning ◽  
The Neural Network ◽  
Learning Techniques ◽  
Out Of Sample

Deep reinforcement learning techniques have demonstrated superior performance in a wide variety of environments. As improvements in training algorithms continue at a brisk pace, theoretical or empirical studies on understanding what these networks seem to learn, are far behind. In this paper we propose an interpretable neural network architecture for Q-learning which provides a global explanation of the model’s behavior using key-value memories, attention and reconstructible embeddings. With a directed exploration strategy, our model can reach training rewards comparable to the state-of-the-art deep Q-learning models. However, results suggest that the features extracted by the neural network are extremely shallow and subsequent testing using out-of-sample examples shows that the agent can easily overfit to trajectories seen during training.

scholarly journals Spatio-Temporal Attention-Based Neural Network for Credit Card Fraud Detection

2020 ◽  
Vol 34 (01) ◽  
pp. 362-369 ◽  
Author(s):  
Dawei Cheng ◽  
Sheng Xiang ◽  
Chencheng Shang ◽  
Yiyi Zhang ◽  
Fangzhou Yang ◽  
...  
Keyword(s):  
Neural Network ◽  
Credit Card ◽  
Domain Knowledge ◽  
Empirical Studies ◽  
Fraud Detection ◽  
Temporal Attention ◽  
Credit Card Fraud ◽  
Domain Experts ◽  
Spatio Temporal ◽  
Better Than

Credit card fraud is an important issue and incurs a considerable cost for both cardholders and issuing institutions. Contemporary methods apply machine learning-based approaches to detect fraudulent behavior from transaction records. But manually generating features needs domain knowledge and may lay behind the modus operandi of fraud, which means we need to automatically focus on the most relevant patterns in fraudulent behavior. Therefore, in this work, we propose a spatial-temporal attention-based neural network (STAN) for fraud detection. In particular, transaction records are modeled by attention and 3D convolution mechanisms by integrating the corresponding information, including spatial and temporal behaviors. Attentional weights are jointly learned in an end-to-end manner with 3D convolution and detection networks. Afterward, we conduct extensive experiments on real-word fraud transaction dataset, the result shows that STAN performs better than other state-of-the-art baselines in both AUC and precision-recall curves. Moreover, we conduct empirical studies with domain experts on the proposed method for fraud post-analysis; the result demonstrates the effectiveness of our proposed method in both detecting suspicious transactions and mining fraud patterns.

scholarly journals Replicate, Walk, and Stop on Syntax: An Effective Neural Network Model for Aspect-Level Sentiment Classification

2020 ◽  
Vol 34 (05) ◽  
pp. 9685-9692
Author(s):  
Yaowei Zheng ◽  
Richong Zhang ◽  
Samuel Mensah ◽  
Yongyi Mao
Keyword(s):  
Neural Network ◽  
Random Walk ◽  
Network Model ◽  
Neural Network Model ◽  
Syntactic Structure ◽  
Contextual Information ◽  
Empirical Studies ◽  
Specific Aspect ◽  
Sentiment Classification ◽  
Benchmark Datasets

Aspect-level sentiment classification (ALSC) aims at predicting the sentiment polarity of a specific aspect term occurring in a sentence. This task requires learning a representation by aggregating the relevant contextual features concerning the aspect term. Existing methods cannot sufficiently leverage the syntactic structure of the sentence, and hence are difficult to distinguish different sentiments for multiple aspects in a sentence. We perceive the limitations of the previous methods and propose a hypothesis about finding crucial contextual information with the help of syntactic structure. For this purpose, we present a neural network model named RepWalk which performs a replicated random walk on a syntax graph, to effectively focus on the informative contextual words. Empirical studies show that our model outperforms recent models on most of the benchmark datasets for the ALSC task. The results suggest that our method for incorporating syntactic structure enriches the representation for the classification.

scholarly journals A recurrent neural network framework for flexible and adaptive decision making based on sequence learning

2020 ◽  
Vol 16 (11) ◽  
pp. e1008342
Author(s):  
Zhewei Zhang ◽  
Huzi Cheng ◽  
Tianming Yang
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Language Processing ◽  
Sequence Learning ◽  
Empirical Studies ◽  
Activity Patterns ◽  
Network Models ◽  
Neural Network Approach ◽  
Encode Task ◽  
The Brain

The brain makes flexible and adaptive responses in a complicated and ever-changing environment for an organism’s survival. To achieve this, the brain needs to understand the contingencies between its sensory inputs, actions, and rewards. This is analogous to the statistical inference that has been extensively studied in the natural language processing field, where recent developments of recurrent neural networks have found many successes. We wonder whether these neural networks, the gated recurrent unit (GRU) networks in particular, reflect how the brain solves the contingency problem. Therefore, we build a GRU network framework inspired by the statistical learning approach of NLP and test it with four exemplar behavior tasks previously used in empirical studies. The network models are trained to predict future events based on past events, both comprising sensory, action, and reward events. We show the networks can successfully reproduce animal and human behavior. The networks generalize the training, perform Bayesian inference in novel conditions, and adapt their choices when event contingencies vary. Importantly, units in the network encode task variables and exhibit activity patterns that match previous neurophysiology findings. Our results suggest that the neural network approach based on statistical sequence learning may reflect the brain’s computational principle underlying flexible and adaptive behaviors and serve as a useful approach to understand the brain.

scholarly journals A Dual-Stage Attention-Based Recurrent Neural Network for Time Series Prediction

2017 ◽  
Author(s):  
Yao Qin ◽  
Dongjin Song ◽  
Haifeng Chen ◽  
Wei Cheng ◽  
Guofei Jiang ◽  
...  
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Recurrent Neural Network ◽  
Empirical Studies ◽  
Time Series Prediction ◽  
Attention Mechanism ◽  
Time Step ◽  
Narx Models ◽  
Dual Stage ◽  
Hidden States

The Nonlinear autoregressive exogenous (NARX) model, which predicts the current value of a time series based upon its previous values as well as the current and past values of multiple driving (exogenous) series, has been studied for decades. Despite the fact that various NARX models have been developed, few of them can capture the long-term temporal dependencies appropriately and select the relevant driving series to make predictions. In this paper, we propose a dual-stage attention-based recurrent neural network (DA-RNN) to address these two issues. In the first stage, we introduce an input attention mechanism to adaptively extract relevant driving series (a.k.a., input features) at each time step by referring to the previous encoder hidden state. In the second stage, we use a temporal attention mechanism to select relevant encoder hidden states across all time steps. With this dual-stage attention scheme, our model can not only make predictions effectively, but can also be easily interpreted. Thorough empirical studies based upon the SML 2010 dataset and the NASDAQ 100 Stock dataset demonstrate that the DA-RNN can outperform state-of-the-art methods for time series prediction.

Neural Network

2007 ◽  
pp. 132-149
Author(s):  
Meliha Handzic
Keyword(s):  
Neural Network ◽  
Knowledge Management ◽  
Empirical Research ◽  
Empirical Studies ◽  
Complete Picture ◽  
Research And Practice ◽  
Management Concepts ◽  
The Impact ◽  
Theoretical Foundations

The book starts with an introduction to theoretical foundations of knowledge management concepts, proceeds with a series of empirical studies on the role of technology in knowledge management, followed by studies of socially orientated knowledge management solutions. The book ends with the discussion of major issues and challenges for knowledge management research and practice. With its integrated and systematic approach, the book makes a small but important step in helping individuals and organisations to get an objective and complete picture of the role of social and technical initiatives in knowledge management based on formal and sound empirical research. More importantly, the book shows that the impact of various initiatives is highly contingent upon the context in which the knowledge is generated, transferred, and used. This may help managers to choose more suitable solutions to turn their intangible assets into tangible outcomes.

Forming Neural Networks Through Efficient and Adaptive Coevolution

1997 ◽  
Vol 5 (4) ◽  
pp. 373-399 ◽  
Author(s):  
David E. Moriarty ◽  
Risto Miikkulainen
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Empirical Studies ◽  
Control Problems ◽  
Control Behavior

This article demonstrates the advantages of a cooperative, coevolutionary search in difficult control problems. The symbiotic adaptive neuroevolution (SANE) system coevolves a population of neurons that cooperate to form a functioning neural network. In this process, neurons assume different but overlapping roles, resulting in a robust encoding of control behavior. SANE is shown to be more efficient and more adaptive and to maintain higher levels of diversity than the more common network-based population approaches. Further empirical studies illustrate the emergent neuron specializations and the different roles the neurons assume in the population.

Gated Neural Network-Based Mean–EVaR–Skewness Portfolio Optimization under Uncertain Environment

2020 ◽  
pp. 2150100
Author(s):  
Sunil Kumar Mittal ◽  
Namita Srivastava
Keyword(s):  
Neural Network ◽  
Portfolio Optimization ◽  
Stock Returns ◽  
Stock Prices ◽  
Empirical Studies ◽  
Central Moment ◽  
Market Uncertainty ◽  
Risk And Return ◽  
Portfolio Returns ◽  
Portfolio Optimization Model

Numerous empirical studies show that portfolio returns are generally asymmetric, and investor would prefer a portfolio return with larger degree of asymmetry along with risk and return. In this paper, a concept of skewness is defined as the third central moment and studied its mathematical properties. To predict the stock prices, a novel recurrent neural network with gated recurrent unit (GRU) cell is preferred. Based on these predictions, stock returns, entropic value at risks and skewness are calculated. A mean–EVaR–skewness multi-objective portfolio optimization model is devised to account for market uncertainty. Cardinality, bounding restrictions, and liquidity are considered in addition to risk and return to make the model more effective. Uncertain goal programming is used to solve the proposed model. Finally, an example portfolio is presented to display the efficacy and the feasibility of the model suggested in this paper.

scholarly journals Risk Guarantee Prediction in Networked-Loans

2020 ◽  
Author(s):  
Dawei Cheng ◽  
Xiaoyang Wang ◽  
Ying Zhang ◽  
Liqing Zhang
Keyword(s):  
Neural Network ◽  
Prediction Accuracy ◽  
State Of The Art ◽  
Empirical Studies ◽  
Experimental Result ◽  
Dynamic Graph ◽  
Form Complex ◽  
Financial Status ◽  
Loan Risk ◽  
Debt Obligation

The guaranteed loan is a debt obligation promise that if one corporation gets trapped in risks, its guarantors will back the loan. When more and more companies involve, they subsequently form complex networks. Detecting and predicting risk guarantee in these networked-loans is important for the loan issuer. Therefore, in this paper, we propose a dynamic graph-based attention neural network for risk guarantee relationship prediction (DGANN). In particular, each guarantee is represented as an edge in dynamic loan networks, while companies are denoted as nodes. We present an attention-based graph neural network to encode the edges that preserve the financial status as well as network structures. The experimental result shows that DGANN could significantly improve the risk prediction accuracy in both the precision and recall compared with state-of-the-art baselines. We also conduct empirical studies to uncover the risk guarantee patterns from the learned attentional network features. The result provides an alternative way for loan risk management, which may inspire more work in the future.

Sign in / Sign up

Export Citation Format

Share Document