Self-localization during navigation with noisy sensors in an ambiguous world is computationally challenging, yet animals and humans excel at it. In robotics, {\em Simultaneous Location and Mapping} (SLAM) algorithms solve this problem through joint sequential probabilistic inference of their own coordinates and those of external spatial landmarks. We generate the first neural solution to the SLAM problem by training recurrent LSTM networks to perform a set of hard 2D navigation tasks that require generalization to completely novel trajectories and environments. Our goal is to make sense of how the diverse phenomenology in the brain's spatial navigation circuits is related to their function. We show that the hidden unit representations exhibit several key properties of hippocampal place cells, including stable tuning curves that remap between environments. Our result is also a proof of concept for end-to-end-learning of a SLAM algorithm using recurrent networks, and a demonstration of why this approach may have some advantages for robotic SLAM.

AI holds promise for transforming scientific processes, including hypothesis generation. Prior work on hypothesis generation can be broadly categorized into theory-driven and data-driven approaches. While both have proven effective in generating novel and plausible hypotheses, it remains an open question whether they can complement each other. To address this, we develop the first method that combines literature-based insights with data to perform LLM-powered hypothesis generation. We apply our method on five different datasets and demonstrate that integrating literature and data outperforms other baselines (8.97\% over few-shot, 15.75\% over literature-based alone, and 3.37\% over data-driven alone). Additionally, we conduct the first human evaluation to assess the utility of LLM-generated hypotheses in assisting human decision-making on two challenging tasks: deception detection and AI generated content detection. Our results show that human accuracy improves significantly by 7.44\% and 14.19\% on these tasks, respectively. These findings suggest that integrating literature-based and data-driven approaches provides a comprehensive and nuanced framework for hypothesis generation and could open new avenues for scientific inquiry.

Large Language Models (LLMs) show impressive inductive reasoning capabilities, enabling them to generate hypotheses that could generalize effectively to new instances when guided by in-context demonstrations. However, in real-world applications, LLMs' hypothesis generation is not solely determined by these demonstrations but is significantly shaped by task-specific model priors. Despite their critical influence, the distinct contributions of model priors versus demonstrations to hypothesis generation have been underexplored. This study bridges this gap by systematically evaluating three inductive reasoning strategies across five real-world tasks with three LLMs. Our empirical findings reveal that, hypothesis generation is primarily driven by the model's inherent priors; removing demonstrations results in minimal loss of hypothesis quality and downstream usage. Further analysis shows the result is consistent across various label formats with different label configurations, and prior is hard to override, even under flipped labeling. These insights advance our understanding of the dynamics of hypothesis generation in LLMs and highlight the potential for better utilizing model priors in real-world inductive reasoning tasks.

An LSTM recurrent neural network is trained to perform simultaneous localization and mapping (SLAM) tasks, given noisy odometry data and occasional input from contacts with walls. The paper is well written and I find it interesting to study recurrent neural network solutions of SLAM. But the idea of using LSTM-RNNs for SLAM problems is not new (as the authors mention in the discussion, line 256) and the results do not really surprise me. Given the amount of training trials, the network has presumably seen sufficiently many trajectories (and variations of the environment) to perform well on most test examples (and if the difference between training and testing error is too large, follow the standard recipes and tune the number of hidden neurons and the number of training trials). A more interesting result would be it the LSTM-RNN would generalize to out of distribution samples, i.e. if its performance would be comparable to that of a PF SLAM in totally different environments than the ones seen during training.

Effective generation of novel hypotheses is instrumental to scientific progress. So far, researchers have been the main powerhouse behind hypothesis generation by painstaking data analysis and thinking (also known as the Eureka moment). In this paper, we examine the potential of large language models (LLMs) to generate hypotheses. We focus on hypothesis generation based on data (i.e., labeled examples). To enable LLMs to handle arbitrarily long contexts, we generate initial hypotheses from a small number of examples and then update them iteratively to improve the quality of hypotheses. Inspired by multi-armed bandits, we design a reward function to inform the exploitation-exploration tradeoff in the update process. Our algorithm is able to generate hypotheses that enable much better predictive performance than few-shot prompting in classification tasks, improving accuracy by 31.7% on a synthetic dataset and by 13.9%, 3.3% and, 24.9% on three real-world datasets. We also outperform supervised learning by 12.8% and 11.2% on two challenging real-world datasets. Furthermore, we find that the generated hypotheses not only corroborate human-verified theories but also uncover new insights for the tasks.

Self-localization during navigation with noisy sensors in an ambiguous world is computationally challenging, yet animals and humans excel at it. In robotics, {\em Simultaneous Location and Mapping} (SLAM) algorithms solve this problem through joint sequential probabilistic inference of their own coordinates and those of external spatial landmarks. We generate the first neural solution to the SLAM problem by training recurrent LSTM networks to perform a set of hard 2D navigation tasks that require generalization to completely novel trajectories and environments. Our goal is to make sense of how the diverse phenomenology in the brain's spatial navigation circuits is related to their function. We show that the hidden unit representations exhibit several key properties of hippocampal place cells, including stable tuning curves that remap between environments.

The growing availability of real-world data has generated tremendous excitement in health care. By some estimates, health data volumes are increasing by 48% annually, and the last decade has seen a boom in the collection and aggregation of this information. Among these data, electronic health records (EHRs) offer one of the biggest opportunities to produce novel insights and disrupt the current understanding of patient care. But analyzing the EHR data requires tools that can process vast amounts of data in short order. Enter artificial intelligence and, more specifically, machine learning, which is already disrupting fields such as drug discovery and medical imaging but only just beginning to scratch the surface of the possible in health care. Let's look at the case of a pharmaceutical company we worked with.

When I reviewed Nebo, MyScript's award-winning, ink-to-digital-text app, I wrote that it's a "game changer" that "sets new standards for accurate handwriting recognition". Nebo's superior accuracy rests on MyScript's interactive ink technology. Recently I had the opportunity to ask MyScript's CTO, Pierre-Michel Lallican, how interactive ink works. Interactive ink is a complex system with three primary modules that are shown in the image at the top of this article. The Digital Ink Management module is the interface between the screen and interactive ink's text recognition and management functions.