Here we adopt the hypothesis that when we are in an interactive social setting, our brains perform Bayesian inference of the intentions and cooperativeness of others using probabilistic representations.

This paper takes a unique approach and aims high. In deep learning, there are all these intriguing empirical observations previously known; the road most travelled to understand them is to prove these observations under certain assumptions, while the authors choose to link these observations through a descriptive model that otherwise could have nothing to do with neural networks. I appreciate this unique approach, which is actually a dominant approach in other sciences like physics. The descriptive model in this paper, if more accurate than not, could potentially simplify the conceptual understanding of optimization for deep learning and motivate new algorithms. There are two reasons why I cannot more enthusiastically recommend this paper.

We introduce ImmerseDiffusion, an end-to-end generative audio model that produces 3D immersive soundscapes conditioned on the spatial, temporal, and environmental conditions of sound objects. ImmerseDiffusion is trained to generate first-order ambisonics (FOA) audio, which is a conventional spatial audio format comprising four channels that can be rendered to multichannel spatial output. The proposed generative system is composed of a spatial audio codec that maps FOA audio to latent components, a latent diffusion model trained based on various user input types, namely, text prompts, spatial, temporal and environmental acoustic parameters, and optionally a spatial audio and text encoder trained in a Contrastive Language and Audio Pretraining (CLAP) style. We propose metrics to evaluate the quality and spatial adherence of the generated spatial audio. Finally, we assess the model performance in terms of generation quality and spatial conformance, comparing the two proposed modes: ``descriptive", which uses spatial text prompts) and ``parametric", which uses non-spatial text prompts and spatial parameters. Our evaluations demonstrate promising results that are consistent with the user conditions and reflect reliable spatial fidelity.

A fundamental problem in cognitive neuroscience is how humans make decisions, act, and behave in relation to other humans. Here we adopt the hypothesis that when we are in an interactive social setting, our brains perform Bayesian inference of the intentions and cooperativeness of others using probabilistic representations. We employ the framework of partially observable Markov decision processes (POMDPs) to model human decision making in a social context, focusing specifically on the volunteer's dilemma in a version of the classic Public Goods Game. We show that the POMDP model explains both the behavior of subjects as well as neural activity recorded using fMRI during the game. The decisions of subjects can be modeled across all trials using two interpretable parameters. Furthermore, the expected reward predicted by the model for each subject was correlated with the activation of brain areas related to reward expectation in social interactions. Our results suggest a probabilistic basis for human social decision making within the framework of expected reward maximization.

"I observed assistive technologies -- developed by scientists and engineers my friends and I never met -- which liberated us. My dream has always been to be one of those engineers." Before James Hermus started elementary school, he was a happy, curious kid who loved to learn. By the end of first grade, however, all that started to change, he says. As his schoolbooks became more advanced, Hermus could no longer memorize the words on each page, and pretend to be reading.

Within process mining, a relevant activity is conformance checking. Such activity consists of establishing the extent to which actual executions of a process conform the expected behavior of a reference model. Current techniques focus on prescriptive models of the control-flow as references. In certain scenarios, however, a prescriptive model might not be available and, additionally, the control-flow perspective might not be ideal for this purpose. This paper tackles these two problems by suggesting a conformance approach that uses a descriptive model (i.e., a pattern of the observed behavior over a certain amount of time) which is not necessarily referring to the control-flow (e.g., it can be based on the social network of handover of work). Additionally, the entire approach can work both offline and online, thus providing feedback in real time. The approach, which is implemented in ProM, has been tested and results from 3 experiments with real world as well as synthetic data are reported.

Humans by their nature have many cognitive biases. This can become detrimental to real scientific progress. Research tends to be bias in favor of approaches that many experts have invested countless years of study. The consequence of this is that we ignore many intrinsic characteristics found in the very system under study. Thus researchers can unfortunately consume a lifetime pursuing a wrong and pointless path. History is littered with research that in hindsight were discovered to be incorrect and therefore worthless.

The pattern theory of Grenander is a mathematical framework where the patterns are represented by probability models on random variables of algebraic structures. In this paper, we review three families of probability models, namely, the discriminative models, the descriptive models, and the generative models. A discriminative model is in the form of a classifier. It specifies the conditional probability of the class label given the input signal. The descriptive model specifies the probability distribution of the signal, based on an energy function defined on the signal. A generative model assumes that the signal is generated by some latent variables via a transformation. We shall review these models within a common framework and explore their connections. We shall also review the recent developments that take advantage of the high approximation capacities of deep neural networks.

Regardless of whether the learner is a human or machine, the basic learning process is similar. Machine learning algorithms are divided into categories according to their purpose. There are lots of overlaps in which ML algorithms are applied to a particular problem. As a result, for the same problem, there could be many different ML models possible. So, coming out with the best ML model is an art that requires a lot of patience and trial and error.

One of the major problems in developing so-called intelligent computer-aided design (CAD) systems (ten Hagen and Tomiyama 1987) is the representation of design knowledge, which is a two-part process: the representation of design objects and the representation of design processes. We believe that intelligent CAD systems will be fully realized only when these two types of representation are integrated. Progress has been made in the representation of design objects, as can be seen, for example, in geometric modeling; however, almost no significant results have been seen in the representation of design processes, which implies that we need a design theory to formalize them. According to Finger and Dixon (1989), design process models can be categorized into a descriptive model that explains how design is done, a cognitive model that explains the designer's behavior, a prescriptive model that shows how design must be done, and a computable model that expresses a method by which a computer can accomplish a task. A design theory for intelligent CAD is not useful when it is merely descriptive or cognitive; it must also be computable.