A major challenge in the use of neural networks both for modeling human cognitive function and for artificial intelligence is the design of systems with the capacity to efficiently learn functions that support radical generalization. At the roots of this is the capacity to discover and implement symmetry functions. In this paper, we investigate a paradigmatic example of radical generalization through the use of symmetry: base addition. We present a group theoretic analysis of base addition, a fundamental and defining characteristic of which is the carry function -- the transfer of the remainder, when a sum exceeds the base modulus, to the next significant place. Our analysis exposes a range of alternative carry functions for a given base, and we introduce quantitative measures to characterize these. We then exploit differences in carry functions to probe the inductive biases of neural networks in symmetry learning, by training neural networks to carry out base addition using different carries, and comparing efficacy and rate of learning as a function of their structure. We find that even simple neural networks can achieve radical generalization with the right input format and carry function, and that learnability is closely correlated with carry function structure. We then discuss the relevance this has for cognitive science and machine learning.

This book offers a hands-on introduction to building and understanding federated learning (FL) systems. FL enables multiple devices -- such as smartphones, sensors, or local computers -- to collaboratively train machine learning (ML) models, while keeping their data private and local. It is a powerful solution when data cannot or should not be centralized due to privacy, regulatory, or technical reasons. The book is designed for students, engineers, and researchers who want to learn how to design scalable, privacy preserving FL systems. Our main focus is on personalization: enabling each device to train its own model while still benefiting from collaboration with relevant devices. This is achieved by leveraging similarities between (the learning tasks associated with) devices that are encoded by the weighted edges (or links) of a federated learning network (FL network). The key idea is to represent real-world FL systems as networks of devices, where nodes correspond to device and edges represent communication links and data similarities between them. The training of personalized models for these devices can be naturally framed as a distributed optimization problem. This optimization problem is referred to as generalized total variation minimization (GTVMin) and ensures that devices with similar learning tasks learn similar model parameters. Our approach is both mathematically principled and practically motivated. While we introduce some advanced ideas from optimization theory and graph-based learning, we aim to keep the book accessible. Readers are guided through the core ideas step by step, with intuitive explanations.

Theoretical physicists describe nature by i) building a theory model and ii) determining the model parameters. The latter step involves the dual aspect of both fitting to the existing experimental data and satisfying abstract criteria like beauty, naturalness, etc. We use the Yukawa quark sector as a toy example to demonstrate how both of those tasks can be accomplished with machine learning techniques. We propose loss functions whose minimization results in true models that are also beautiful as measured by three different criteria - uniformity, sparsity, or symmetry.

There is an increasing consensus about the effectiveness of user-centred approaches in the explainable artificial intelligence (XAI) field. Indeed, the number and complexity of personalised and user-centred approaches to XAI have rapidly grown in recent years. Often, these works have a two-fold objective: (1) proposing novel XAI techniques able to consider the users and (2) assessing the \textit{goodness} of such techniques with respect to others. From these new works, it emerged that user-centred approaches to XAI positively affect the interaction between users and systems. However, so far, the goodness of XAI systems has been measured through indirect measures, such as performance. In this paper, we propose an assessment task to objectively and quantitatively measure the goodness of XAI systems in terms of their \textit{information power}, which we intended as the amount of information the system provides to the users during the interaction. Moreover, we plan to use our task to objectively compare two XAI techniques in a human-robot decision-making task to understand deeper whether user-centred approaches are more informative than classical ones.

Every once in a while, you encounter a research paper that is so simple and yet profound and brilliant that makes you wish you would have written it yourself. That's how I felt when I read Francois Collet's On the Measure of Intelligence. The paper resonated with me not only because it confronts some of the key philosophical and technical challenges about artificial intelligence(AI) systems that I have been spending some time on but also because it does so in such an elegant way that is hard to argue with. Mr. Collet's thesis is remarkably simple: for AI systems to reach its potential, we need quantitative and actionable methods that measure intelligence in a way that shows similarities with human cognition. Mr. Collet's thesis might seem contradictory given the recent achievements of AI systems.

The ability of digital storytelling agents to evaluate their output is important for ensuring high-quality human-agent interactions. However, evaluating stories remains an open problem. Past evaluative techniques are either model-specific--- which measure features of the model but do not evaluate the generated stories ---or require direct human feedback, which is resource-intensive. We introduce a number of story features that correlate with human judgments of stories and present algorithms that can measure these features. We find this approach results in a proxy for human-subject studies for researchers evaluating story generation systems.

The variability of the clusters generated by clustering techniques in the domain of latitude and longitude variables of fatal crash data are significantly unpredictable. This unpredictability, caused by the randomness of fatal crash incidents, reduces the accuracy of crash frequency (i.e., counts of fatal crashes per cluster) which is used to measure traffic safety in practice. In this paper, a quantitative measure of traffic safety that is not significantly affected by the aforementioned variability is proposed. It introduces a fatal point -- a segment with the highest frequency of fatality -- concept based on cluster characteristics and detects them by imposing rounding errors to the hundredth decimal place of the longitude. The frequencies of the cluster and the cluster's fatal point are combined to construct a low-sensitive quantitative measure of traffic safety for the cluster. The performance of the proposed measure of traffic safety is then studied by varying the parameter k of k-means clustering with the expectation that other clustering techniques can be adopted in a similar fashion. The 2015 North Carolina fatal crash dataset of Fatality Analysis Reporting System (FARS) is used to evaluate the proposed fatal point concept and perform experimental analysis to determine the effectiveness of the proposed measure. The empirical study shows that the average traffic safety, measured by the proposed quantitative measure over several clusters, is not significantly affected by the variability, compared to that of the standard crash frequency.

Audio super-resolution aims to reconstruct a high-resolution audio waveform given a lower-resolution waveform as input. There are several potential applications for this type of upsampling in such areas as streaming audio and audio restoration. One traditional solution is to use a database of audio clips to fill in the missing frequencies in the downsampled waveform using a similarity metric (see this and this paper). Inspired by the successful applications of deep learning to image super-resolution, there is recent interest in using deep neural networks to accomplish this upsampling on raw audio waveforms. After prototyping several methods, I focused on implementing and customizing recently published research from the 2017 International Conference on Learning Representations (ICLR).