1. |
- Blad, Samuel, 1988-, et al.
(author)
-
Empirical analysis of the convergence of Double DQN in relation to reward sparsity
- 2022
-
In: 21st IEEE International Conference on Machine Learning and Applications. ICMLA 2022. - : IEEE. - 9781665462839 - 9781665462846 ; , s. 591-596
-
Conference paper (peer-reviewed)abstract
- Q-Networks are used in Reinforcement Learning to model the expected return from every action at a given state. When training Q-Networks, external reward signals are propagated to the previously performed actions leading up to each reward. If many actions are required before experiencing a reward, the reward signal is distributed across all those actions, where some actions may have greater impact on the reward than others. As the number of significant actions between rewards increases, the relative importance of each action decreases. If actions have too small importance, their impact might be over-shadowed by noise in a deep neural network model, potentially causing convergence issues. In this work, we empirically test the limits of increasing the number of actions leading up to a reward in a simple grid-world environment. We show in our experiments that even though the training error surpasses the reward signal attributed to each action, the model is still able to learn a smooth enough value representation.
|
|
2. |
- Svahn, Caroline, et al.
(author)
-
CCVAE: A Variational Autoencoder for Handling Censored Covariates
- 2022
-
In: 2022 21ST IEEE INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND APPLICATIONS, ICMLA. - : IEEE COMPUTER SOC. - 9781665462839 - 9781665462846 ; , s. 709-714
-
Conference paper (peer-reviewed)abstract
- For time or safety critical scenarios when faulty predictions or decisions can have crucial consequences, such as in certain telecommunications scenarios, reliable prediction models and accurate data are of the essence. When modeling and predicting data in such scenarios, data with censored covariates remain an issue as ignoring them or imputing them with lack of precision may cause inaccurate or uncertain predictions. In this paper, we provide a fast, reliable Variational Autoencoder framework which can handle covariate censoring in high dimensional data. Our numerical experiments demonstrate that our framework compares favorably to alternative methods in terms of prediction accuracy for both the response and the covariates, while enabling estimation of the prediction uncertainties. We moreover demonstrate that the method is at least 8 times faster than the benchmark models used in this paper, and more robust to initial imputations and noise than existing models. The method can also be used directly for predicting unseen data, which is a challenge for some state-of-the-art methods.
|
|
3. |
- Sweidan, Dirar, et al.
(author)
-
Predicting Customer Churn in Retailing
- 2022
-
In: Proceedings 21st IEEE International Conference on Machine Learning and Applications ICMLA 2022. - : IEEE. - 9781665462839 - 9781665462846 ; , s. 635-640
-
Conference paper (peer-reviewed)abstract
- Customer churn is one of the most challenging problems for digital retailers. With significantly higher costs for acquiring new customers than retaining existing ones, knowledge about which customers are likely to churn becomes essential. This paper reports a case study where a data-driven approach to churn prediction is used for predicting churners and gaining insights about the problem domain. The real-world data set used contains approximately 200 000 customers, describing each customer using more than 50 features. In the pre-processing, exploration, modeling and analysis, attributes related to recency, frequency, and monetary concepts are identified and utilized. In addition, correlations and feature importance are used to discover and understand churn indicators. One important finding is that the churn rate highly depends on the number of previous purchases. In the segment consisting of customers with only one previous purchase, more than 75% will churn, i.e., not make another purchase in the coming year. For customers with at least four previous purchases, the corresponding churn rate is around 25%. Further analysis shows that churning customers in general, and as expected, make smaller purchases and visit the online store less often. In the experimentation, three modeling techniques are evaluated, and the results show that, in particular, Gradient Boosting models can predict churners with relatively high accuracy while obtaining a good balance between precision and recall.
|
|
4. |
- Almeida, Tiago Rodrigues de, 1996-, et al.
(author)
-
Context-free Self-Conditioned GAN for Trajectory Forecasting
- 2022
-
In: 21st IEEE International Conference on Machine Learning and Applications. ICMLA 2022. - : IEEE. - 9781665462839 ; , s. 1218-1223
-
Conference paper (peer-reviewed)abstract
- In this paper, we present a context-free unsupervised approach based on a self-conditioned GAN to learn different modes from 2D trajectories. Our intuition is that each mode indicates a different behavioral moving pattern in the discriminator's feature space. We apply this approach to the problem of trajectory forecasting. We present three different training settings based on self-conditioned GAN, which produce better forecasters. We test our method in two data sets: human motion and road agents. Experimental results show that our approach outperforms previous context-free methods in the least representative supervised labels while performing well in the remaining labels. In addition, our approach outperforms globally in human motion, while performing well in road agents.
|
|
5. |
- Markovic, Tijana, et al.
(author)
-
Software package for regression algorithms based on Gaussian Conditional Random Fields
- 2022
-
In: Proceedings - 21st IEEE International Conference on Machine Learning and Applications, ICMLA 2022. - : Institute of Electrical and Electronics Engineers Inc.. - 9781665462839 ; , s. 1121-1128
-
Conference paper (peer-reviewed)abstract
- The Gaussian Conditional Random Fields (GCRF) algorithm and its extensions are used for machine learning regression problems in which the attributes of objects and the correlation between objects should be considered when making predictions. These algorithms can be applied in different domains where problems can be seen as graphs, but their implementation requires complex calculations and good programming skills. This paper presents an open source software package that includes a tool with graphical user interface (GCRFs tool) and Java library (GCRFs library). GCRFs tool is software that integrates various GCRF-based algorithms and supports training and testing of those algorithms on real-world datasets. The main goal of GCRFs tool is to provide a straightforward and user-friendly graphical user interface that will simplify the use of GCRF-based algorithms. GCRFs Java library contains basic classes for GCRF concepts and can be used by researchers who have experience in Java programming. Also, this paper presents the results of a pilot usability evaluation of the GCRFs tool, where the software was evaluated with expert and non-expert users. This evaluation gave us detailed insight into the experiences and opinions of the users and helped us outline priorities for future development.
|
|