Ieee Transactions on Knowledge and Data Engineering 1 towards Bayesian Deep Learning: a Framework and Some Existing Methods

By Hao Wang, Dit-Yan Yeung

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Swagatam Das
2. Hao Wang
3. Dit-Yan Yeung
4. Yi Tay
5. Seyedali Mirjalili
6. Jun Shu
7. Javier Del Ser
8. Xin-She Yang

Citations in the corpus

• Natural-Parameter Networks: A Class of Probabilistic Neural Networks (2016, background): “As possible extensions of NPN, it would be interesting to connect NPN to arbitrary PGM to form fully Bayesian deep learning models [24, 25], allowing even richer descriptions of relationships among latent variables.”
• Hands-On Bayesian Neural Networks—A Tutorial for Deep Learning Users (2020, background): “tand many regularization techniques and learning strategies that are already used in classic deep learning [69]. There is a rich literature in the field of Bayesian (deep) learning, including reviews [50, 85, 89], but none of which explores, in a specific and exhaustive way, the general theory of Ba”
• Deep learning in cancer diagnosis, prognosis and treatment selection (2021, unknown): “quantifying prediction uncertainty, such as Bayesian DL [161], are great candidates to address these issues and have recently started to be applied in cancer diagnosis”
• Deep Learning Based Recommender System (2017, background): “ked denoising autoencoder (SDAE) into probabilistic matrix factorization. To seamlessly combine deep learning and recommendation model, the authors proposed a general Bayesian deep learning framework [161] consisting of two tightly hinged components: perception component (deep neural network) and ta”
• Can deep learning beat numerical weather prediction? (2021, methodology): “However, these methods do not scale well for high-dimensional and high-volume data [134–136].”
• A Survey on Security Threats and Defensive Techniques of Machine Learning: A Data Driven View (2018, background): “, Bayes deep networks with prior information [110].”
• Small Sample Learning in Big Data Era (2018, background): “Another attempt called Bayesian deep learning (Wang and Yeung, 2016) integrated deep learning and Bayesian models within a principled probabilistic framework.”
• Explainable AI (XAI): A Systematic Meta-Survey of Current Challenges and Future Opportunities (2021, methodology): “In a recent survey on Bayesian DL (BDL) [103] this complement observation has been exploited, and a general framework for BDL within a uniform probabilistic framework has been proposed.”
• Relational Deep Learning: A Deep Latent Variable Model for Link Prediction (2017, methodology): “The first dataset, citeulike-a, is mostly from (Wang and Blei 2011) and the second dataset, citeulike-t, was collected independently of the first one (Wang, Chen, and Li 2013).”
• Introduction to MAchine Learning & Knowledge Extraction (MAKE) (2017, background): “This insights call for merging probabilistic graphical models with deep learning approaches (see the survey by WANG and YEUNG (2016) [60]).”
• Deep Learning for Anomaly Detection (2020, unknown): “Different Bayesian deep learning techniques [156] may be adapted for anomaly detection.”
• A survey of uncertainty in deep neural networks (2021, background): “contributed two surveys on Bayesian deep learning [53], [54].”
• Collaborative Recurrent Autoencoder: Recommend while Learning to Fill in the Blanks (2016, methodology): “From the generative process, we can see that both CRAE and CDL are Bayesian deep learning (BDL) models (as described in [24]) with a perception component (DRAE in CRAE) and a task-specific component.”
• Drawbacks of Artificial Intelligence and Their Potential Solutions in the Healthcare Sector (2023, background): “And the results should again be revised under clinical and biological terms [53].”
• Bio-inspired computation: Where we stand and what's next (2019, background): “[203] or provided off-the-shelf by Bayesian deep models [204].”
• Explainable artificial intelligence: a comprehensive review (2021, background): “Wang and Yeung (2016) proposed a novel Bayesian deep learning (BDL) framework to obtain combined intelligence that supported the inference of the output.”
• Accelerating the discovery of materials for clean energy in the era of smart automation (2018, unknown): “Examples of hybrid learning models include Bayesian deep learning 44 , Bayesian conditional generative adversarial networks 45 and deep Bayesian optimization 46 .”
• ProbGAN: Towards Probabilistic GAN with Theoretical Guarantees (2018, background): “We hope that our work helps inspire continued exploration into Bayesian deep learning (Wang & Yeung, 2016) from a more rigorous perspective.”