Automatic drum transcription is a critical tool in Music Information Retrieval for extracting and analyzing the rhythm of a music track, but it is limited by the size of the datasets available for training. A popular method used to increase the amount of data is by generating them synthetically from music scores rendered with virtual instruments. This method can produce a virtually infinite quantity of tracks, but empirical evidence shows that models trained on previously created synthetic datasets do not transfer well to real tracks. In this work, besides increasing the amount of data, we identify and evaluate three more strategies that practitioners can use to improve the realism of the generated data and, thus, narrow the synthetic-to-real transfer gap. To explore their efficacy, we used them to build a new synthetic dataset and then we measured how the performance of a model scales and, specifically, at what value it will stagnate when increasing the number of training tracks for different datasets. By doing this, we were able to prove that the aforementioned strategies contribute to make our dataset the one with the most realistic data distribution and the lowest synthetic-to-real transfer gap among the synthetic datasets we evaluated. We conclude by highlighting the limits of training with infinite data in drum transcription and we show how they can be overcome.

Program synthesis or code generation aims to generate a program that satisfies a problem specification. Recent approaches using large-scale pretrained language models (LMs) have shown promising results, yet they have some critical limitations. In particular, they often follow a standard supervised fine-tuning procedure to train a code generation model only from the pairs of natural-language problem descriptions and ground-truth programs. Such paradigm largely ignores some important but potentially useful signals in the problem specification such as unit tests, which thus often results in poor performance when solving complex unseen coding tasks. To address the limitations, we propose "CodeRL", a new framework for program synthesis tasks through pretrained LMs and deep reinforcement learning (RL). Specifically, during training, we treat the code-generating LM as an actor network, and introduce a critic network that is trained to predict the functional correctness of generated programs and provide dense feedback signals to the actor. During inference, we introduce a new generation procedure with a critical sampling strategy that allows a model to automatically regenerate programs based on feedback from example unit tests and critic scores. For the model backbones, we extended the encoder-decoder architecture of CodeT5 with enhanced learning objectives, larger model sizes, and better pretraining data. Our method not only achieves new SOTA results on the challenging APPS benchmark, but also shows strong zero-shot transfer capability with new SOTA results on the simpler MBPP benchmark.

The Angry Birds AI competition has been held over many years to encourage the development of AI agents that can play Angry Birds game levels better than human players. Many different agents with various approaches have been employed over the competition's lifetime to solve this task. Even though the performance of these agents has increased significantly over the past few years, they still show major drawbacks in playing deceptive levels. This is because most of the current agents try to identify the best next shot rather than planning an effective sequence of shots. In order to encourage advancements in such agents, we present an automated methodology to generate deceptive game levels for Angry Birds. Even though there are many existing content generators for Angry Birds, they do not focus on generating deceptive levels. In this paper, we propose a procedure to generate deceptive levels for six deception categories that can fool the state-of-the-art Angry Birds playing AI agents. Our results show that generated deceptive levels exhibit similar characteristics of human-created deceptive levels. Additionally, we define metrics to measure the stability, solvability, and degree of deception of the generated levels.

Raven’s Progressive Matrices (RPMs) are a popular family of general intelligence tests, and provide a non-verbal measure of a test subject’s reasoning abilities. Traditionally RPMs have been manually designed. To make them readily available for both practice and examination, we tackle the problem of automatically synthesizing RPMs. Our goal is to efficiently generate a large number of RPMs that are authentic (i.e. similar to manually written problems), interesting (i.e. diverse in terms of difficulty), and well-formed (i.e unambiguous). The main technical challenges are: How to formalize RPMs to accommodate their seemingly enormous diversity, and how to define and enforce their validity? To this end, we (1) introduce an abstract representation of RPMs using first-order logic, and (2) restrict instantiations to only valid RPMs. We have realized our approach and evaluated its efficiency and effectiveness. We show that our system can generate hundreds of valid problems per second with varying levels of difficulty. More importantly, we show, via a user study with 24 participants, that the generated problems are statistically indistinguishable from actual problems. This work is an exciting instance of how logic and reasoning may aid general learning.

Note: PDF of full volume downloadable by clicking on title above (26 MB). Selected individual chapters available from the links below. CONTENTSINTRODUCTION MATHEMATICAL FOUNDATIONS1 The morphology of prex—an essay in meta-algorithmics. J. LAS KS 32 Program schemata. M. S. PATE RSON 193 Language definition and compiler validation. J. J. FLORENTIN 334 Placing trees in lexicographic order. H. I.S COINS 43 THEOREM PROVING5 A new look at mathematics and its mechanization. B. M ELTZER 636 Some notes on resolution strategies. B. MELTZER 717 The generalized resolution principle. J. A. ROBINSON 778 Some tree-paring strategies for theorem proving. D.LUCKHAM 959 Automatic theorem proving with equality substitutions andmathematical induction. J. L. D ARLINGTON 113 MACHINE LEARNING AND HEURISTIC PROGRAMMING10 On representations of problems of reasoning about actions.S.AMAREL 13111 Descriptions. E.W.ELCOCK 17312 Kalah on Atlas. A.G.BELL 18113 Experiments with a pleasure-seeking automaton: J. E. DORAN 19514 Collective behaviour and control problems. V.I.VARSHAVSKY 217 MAN—MACHINE INTERACTION15 A comparison of heuristic, interactive, and unaided methods ofsolving a shortest-route problem. D.MICHIE, J. G. FLEMING andJ. V.OLDFIELD 24516 Interactive programming at Carnegie Tech. A.H.BOND 25717 Maintenance of large computer systems—the engineer's assistant.M.H.J.BAYLIS 269 COGNITIVE PROCESSES: METHODS AND MODELS18 The syntactic analysis of English by machine. J.P.THORNE,P.BRATLEY and H.DEWAR 28119 The adaptive memorization of sequences. H.C.LONOUETHIGGINSand A.ORTONY 311 PATTERN RECOGNITION20 An application of Graph Theory in pattern recognition.C.J.HILDITCH 325 PROBLEM-ORIENTED LANGUAGES21 Some semantics for data structures. D. PARK 35122 Writing search algorithms in functional form. R.M.BURSTALL 37323 Assertions: programs written without specifying unnecessaryorder. J.M.FOSTER 38724 The design philosophy of Pop-2. R.J.POPPLESTONE 393 INDEX 403 Machine Intelligence Workshop