Actively Semi-Supervised Deep Rule-based Classifier Applied to Adverse Driving Scenarios

Soares, Eduardo; Angelov, Plamen; Costa, Bruno Sielly Jales; Castro, Marcos

doi:10.1109/ijcnn.2019.8851842

Cited by 12 publications

(11 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, the proposed xDNN has at its top layer a set of a very small number of MegaClouds (27 or, on average, 4 MegaClouds per class) which makes it very easy to explain and visualize. For comparison, our earlier version of deep rule-based models, called DRB [17] also produced a high accuracy and was trained a bit faster, but ended up with 521 prototypes (on average 75 prototypes per class) [26]. With xDNN we do generate meaningful IF...T HEN rules as well as generate an analytical description of the typicality which is the empirically derived pdf in a closed form which lends itself for further analysis and processing.…”

Section: Results and Analysismentioning

confidence: 99%

“…With xDNN we do generate meaningful IF...T HEN rules as well as generate an analytical description of the typicality which is the empirically derived pdf in a closed form which lends itself for further analysis and processing. [26] 99.51 % 836.28 Not reported DRB [26] 99.02% 2.95 521 SVM [26] 94.17% 5.67 Not reported KNN [26] 93.49% 4.43 4656 Naive Bayes [26] 88.35%…”

Section: Results and Analysismentioning

confidence: 99%

See 1 more Smart Citation

Towards explainable deep neural networks (xDNN)

2020

Self Cite

View full text Add to dashboard Cite

In this paper, we propose an elegant solution that is directly addressing the bottlenecks of the traditional deep learning approaches and offers a clearly explainable internal architecture that can outperform the existing methods, requires very little computational resources (no need for GPUs) and short training times (in the order of seconds). The proposed approach, xDNN is using prototypes. Prototypes are actual training data samples (images), which are local peaks of the empirical data distribution called typicality as well as of the data density. This generative model is identified in a closed form and equates to the pdf but is derived automatically and entirely from the training data with no user-or problemspecific thresholds, parameters or intervention. The proposed xDNN offers a new deep learning architecture that combines reasoning and learning in a synergy. It is non-iterative and non-parametric, which explains its efficiency in terms of time and computational resources. From the user perspective, the proposed approach is clearly understandable to human users. We tested it on some well-known benchmark data sets such as iRoads and Caltech-256. xDNN outperforms the other methods including deep learning in terms of accuracy, time to train and offers a clearly explainable classifier. In fact, the result on the very hard Caltech-256 problem (which has 257 classes) represents a world record [1].

show abstract

Section: Results and Analysismentioning

confidence: 99%

Section: Results and Analysismentioning

confidence: 99%

Towards explainable deep neural networks (xDNN)

2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…• Deep Rule-based(DRB) classification [29]: DRB is a semi-supervised non-parametric approach based on human-understandable (IF..THEN) fuzzy rules, as shown in fig. 16.…”

Section: Scene Recognitionmentioning

confidence: 99%

Continual Learning for Real-World Autonomous Systems: Algorithms, Challenges and Frameworks

Shaheen¹,

Hanif²,

Hasan³

et al. 2021

Preprint

View full text Add to dashboard Cite

Continual learning is essential for all real-world applications, as frozen pre-trained models cannot effectively deal with non-stationary data distributions. The purpose of this study is to review the state-of-the-art methods that allow continuous learning of computational models over time. We primarily focus on the learning algorithms that perform continuous learning in an online fashion from considerably large (or infinite) sequential data and require substantially low computational and memory resources. We critically analyze the key challenges associated with continual learning for autonomous real-world systems and compare current methods in terms of computations, memory, and network/model complexity. We also briefly describe the implementations of continuous learning algorithms under three main autonomous systems, i.e., self-driving vehicles, unmanned aerial vehicles, and robotics. The learning methods of these autonomous systems and their strengths and limitations are extensively explored in this article.

show abstract

“…Then the m-σ rule is applied, for detailed explanation about the m-σ please refer to [20]. New classes are actively added by the proposed xClass classifier when the inequality ( 14) is satisfied and rules are actively created.…”

Section: Drop Of Confidence (Detect the Novelty)mentioning

confidence: 99%

Novelty Detection and Learning from Extremely Weak Supervision

Soares,

Angelov

2019

Preprint

Self Cite

View full text Add to dashboard Cite

In this paper we offer a method and algorithm, which make possible fully autonomous (unsupervised) detection of new classes, and learning following a very parsimonious training priming (few labeled data samples only). Moreover, new unknown classes may appear at a later stage and the proposed xClass method and algorithm are able to successfully discover this and learn from the data autonomously. Furthermore, the features (inputs to the classifier) are automatically sub-selected by the algorithm based on the accumulated data density per feature per class. As a result, a highly efficient, lean, human-understandable, autonomously self-learning model (which only needs an extremely parsimonious priming) emerges from the data. To validate our proposal we tested it on two challenging problems, including imbalanced Caltech-101 data set and iRoads dataset. Not only we achieved higher precision, but, more significantly, we only used a single class beforehand, while other methods used all the available classes) and we generated interpretable models with smaller number of features used, through extremely weak and weak supervision.

show abstract

Actively Semi-Supervised Deep Rule-based Classifier Applied to Adverse Driving Scenarios

Cited by 12 publications

References 28 publications

Towards explainable deep neural networks (xDNN)

Towards explainable deep neural networks (xDNN)

Continual Learning for Real-World Autonomous Systems: Algorithms, Challenges and Frameworks

Novelty Detection and Learning from Extremely Weak Supervision

Contact Info

Product

Resources

About