| 1. |
- Eiter, Thomas, et al.
(författare)
-
Large-Neighbourhood Search for Optimisation in Answer-Set Solving
- 2022
-
Ingår i: Proceedings of the 36th AAAI Conference on Artificial Intelligence, AAAI 2022. - : Association for the Advancement of Artificial Intelligence. - 1577358767 - 9781577358763 ; , s. 5616-5625
-
Konferensbidrag (refereegranskat)abstract
- While Answer-Set Programming (ASP) is a prominent approach to declarative problem solving, optimisation problems can still be a challenge for it. Large-Neighbourhood Search (LNS) is a metaheuristic for optimisation where parts of a solution are alternately destroyed and reconstructed that has high but untapped potential for ASP solving. We present a framework for LNS optimisation in answer-set solving in which neighbourhoods can be specified either declaratively as part of the ASP encoding or automatically generated by code. To effectively explore different neighbourhoods, we focus on multi-shot solving as it allows to avoid program regrounding. We illustrate the framework on different optimisation problems some of which are notoriously difficult, including shift planning and a parallel machine scheduling problem from semi-conductor production, which demonstrate the effectiveness of the LNS approach.
|
|
| 2. |
- Geldhauser, Carina, et al.
(författare)
-
I AM A.I. Gradient Descent - an Open-Source Digital Game for Inquiry-Based CLIL Learning
- 2022
-
Ingår i: IAAI-22, EAAI-22, AAAI-22 Special Programs and Special Track, Student Papers and Demonstrations. - : Association for the Advancement of Artificial Intelligence (AAAI). - 1577358767 - 9781577358763 ; 36, s. 12751-12757
-
Konferensbidrag (refereegranskat)abstract
- We present an interactive online workshop for K-12 students, which aims in familiarizing students with core concepts of AI. The workshop consists of a variety of resources, inspired by inquiry-based learning techniques, of which we present in detail one module, centered around a browser-based game called “Gradient Descent”. This module introduces the mathematical concepts behind a gradient descent-based optimization algorithm through the computer game of a treasure hunt at an unknown sea surface landscape. Finally, we report on student feedback for the module in a series of content and language integrated learning in German (CLiLiG) workshops for students aged 14-17 in 30 countries.
|
|
| 3. |
- Verreet, Victor, et al.
(författare)
-
Inference and Learning with Model Uncertainty in Probabilistic Logic Programs
- 2022
-
Ingår i: Proceedings of the 36th AAAI Conference on Artificial Intelligence. - : AAAI Press. - 1577358767 - 9781577358763 ; , s. 10060-10069
-
Konferensbidrag (refereegranskat)abstract
- An issue that has so far received only limited attention in probabilistic logic programming (PLP) is the modelling of so-called epistemic uncertainty, the uncertainty about the model itself. Accurately quantifying this model uncertainty is paramount to robust inference, learning and ultimately decision making. We introduce BetaProbLog, a PLP language that can model epistemic uncertainty. BetaProbLog has sound semantics, an effective inference algorithm that combines Monte Carlo techniques with knowledge compilation, and a parameter learning algorithm. We empirically outperform state-of-the-art methods on probabilistic inference tasks in second-order Bayesian networks, digit classification and discriminative learning in the presence of epistemic uncertainty.
|
|
| 4. |
- Dabrowski, Konrad K., et al.
(författare)
-
Resolving Inconsistencies in Simple Temporal Problems: A Parameterized Approach
- 2022
-
Ingår i: THIRTY-SIXTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTY-FOURTH CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE / THE TWELVETH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE. - : ASSOC ADVANCEMENT ARTIFICIAL INTELLIGENCE. - 9781577358763 ; , s. 3724-3732
-
Konferensbidrag (refereegranskat)abstract
- The simple temporal problem (STP) is one of the most influential reasoning formalisms for representing temporal information in AL We study the problem of resolving inconsistency of data encoded in the STP. We prove that the problem of identifying a maximally large consistent subset of data is NP-hard. In practical instances, it is reasonable to assume that the amount of erroneous data is small. We therefore parameterize by the number of constraints that need to be removed to achieve consistency. Using tools from parameterized complexity we design fixed-parameter tractable algorithms for two large fragments of the STP. Our main algorithmic results employ reductions to the Directed Subset Feedback Arc Set problem and iterative compression combined with an efficient algorithm for the Edge Multicut problem. We complement our algorithmic results with hardness results that rule out fixed-parameter tractable algorithms for all remaining non-trivial fragments of the STP (under standard complexity-theoretic assumptions). Together, our results give a full classification of the classical and parameterized complexity of the problem.
|
|
| 5. |
- Geffner, Hector
(författare)
-
Target Languages (vs. Inductive Biases) for Learning to Act and Plan
- 2022
-
Ingår i: THIRTY-SIXTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTY-FOURTH CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE / TWELVETH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE. - : ASSOC ADVANCEMENT ARTIFICIAL INTELLIGENCE. - 9781577358763 ; , s. 12326-12333
-
Konferensbidrag (refereegranskat)abstract
- Recent breakthroughs in AI have shown the remarkable power of deep learning and deep reinforcement learning. These developments, however, have been tied to specific tasks, and progress in out-of-distribution generalization has been limited. While it is assumed that these limitations can be overcome by incorporating suitable inductive biases, the notion of inductive biases itself is often left vague and does not provide meaningful guidance. In the paper, I articulate a different learning approach where representations do not emerge from biases in a neural architecture but are learned over a given target language with a known semantics. The basic ideas are implicit in mainstream AI where representations have been encoded in languages ranging from fragments of first-order logic to probabilistic structural causal models. The challenge is to learn from data, the representations that have traditionally been crafted by hand. Generalization is then a result of the semantics of the language. The goals of this paper are to make these ideas explicit, to place them in a broader context where the design of the target language is crucial, and to illustrate them in the context of learning to act and plan. For this, after a general discussion, I consider learning representations of actions, general policies, and subgoals ("intrinsic rewards"). In these cases, learning is formulated as a combinatorial problem but nothing prevents the use of deep learning techniques instead. Indeed, learning representations over languages with a known semantics provides an account of what is to be learned, while learning representations with neural nets provides a complementary account of how representations can be learned. The challenge and the opportunity is to bring the two together.
|
|
| 6. |
- Johnson, David, et al.
(författare)
-
An Experience Report of Executive-Level Artificial Intelligence Education in the United Arab Emirates
- 2022
-
Ingår i: Proceedings of the 36th AAAI Conference on Artificial Intelligence. - : Association for the Advancement of Artificial Intelligence (AAAI). ; , s. 12766-12773, s. 12766-12773
-
Konferensbidrag (refereegranskat)abstract
- Teaching artificial intelligence (AI) is challenging. It is a fast moving field and therefore difficult to keep people updated with the state-of-the-art. Educational offerings for students are ever increasing, beyond university degree programs where AI education traditionally lay. In this paper, we present an experience report of teaching an AI course to business executives in the United Arab Emirates (UAE). Rather than focusing only on theoretical and technical aspects, we developed a course that teaches AI with a view to enabling students to understand how to incorporate it into existing business processes. We present an overview of our course, curriculum and teaching methods, and we discuss our reflections on teaching adult learners, and to students in the UAE.
|
|
| 7. |
- Kiessling, Jonas, et al.
(författare)
-
A Computable Definition of the Spectral Bias
- 2022
-
Ingår i: Proceedings of the 36th AAAI Conference on Artificial Intelligence, AAAI 2022. - : Association for the Advancement of Artificial Intelligence. ; 36:7, s. 7168-7175
-
Konferensbidrag (refereegranskat)abstract
- Neural networks have a bias towards low frequency functions. This spectral bias has been the subject of several previous studies, both empirical and theoretical. Here we present a computable definition of the spectral bias based on a decomposition of the reconstruction error into a low and a high frequency component. The distinction between low and high frequencies is made in a way that allows for easy interpretation of the spectral bias. Furthermore, we present two methods for estimating the spectral bias. Method 1 relies on the use of the discrete Fourier transform to explicitly estimate the Fourier spectrum of the prediction residual, and Method 2 uses convolution to extract the low frequency components, where the convolution integral is estimated by Monte Carlo methods. The spectral bias depends on the distribution of the data, which is approximated with kernel density estimation when unknown. We devise a set of numerical experiments that confirm that low frequencies are learned first, a behavior quantified by our definition.
|
|
| 8. |
- Lindenberg, Björn, Doktorand, 1978-, et al.
(författare)
-
Conjugated Discrete Distributions for Distributional Reinforcement Learning
- 2022
-
Ingår i: Proceedings of the AAAI Conference on Artificial Intelligence. - : Association for the advancement of artificial intelligence. - 2374-3468 .- 2159-5399. - 9781577358763 ; , s. 7516-7524
-
Konferensbidrag (refereegranskat)abstract
- In this work we continue to build upon recent advances in reinforcement learning for finite Markov processes. A common approach among previous existing algorithms, both single-actor and distributed, is to either clip rewards or to apply a transformation method on Q-functions to handle a large variety of magnitudes in real discounted returns. We theoretically show that one of the most successful methods may not yield an optimal policy if we have a non-deterministic process. As a solution, we argue that distributional reinforcement learning lends itself to remedy this situation completely. By the introduction of a conjugated distributional operator we may handle a large class of transformations for real returns with guaranteed theoretical convergence. We propose an approximating single-actor algorithm based on this operator that trains agents directly on unaltered rewards using a proper distributional metric given by the Cramér distance. To evaluate its performance in a stochastic setting we train agents on a suite of 55 Atari 2600 games using sticky-actions and obtain state-of-the-art performance compared to other well-known algorithms in the Dopamine framework.
|
|
