A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
A novel memory mechanism for reinforcement learning agents that stores past events in human-readable language.
Typical neural networks with external memory do not effectively separate capacity for episodic and working memory as is required for reasoning in humans. Applying knowledge gained from psychological studies, we designed a new model called Differentiable Working Memory (DWM) in order to specifically emulate human workin…
Enhanced financial trading system using multi-agent LLMs with layered memory.
We investigate the robustness properties of image recognition models equipped with two features inspired by human vision, an explicit episodic memory and a shape bias, at the ImageNet scale. As reported in previous work, we show that an explicit episodic memory improves the robustness of image recognition models agains…
Mindful active learning improves activity recognition using wearable sensors.
Researchers develop a neural network that learns like humans, overcoming forgetting and structure issues.
Tensor models decode human perception and memory using SPO triples.
AI beats 95% of humans in Rock-Paper-Scissors.
The paper benchmarks data stream classifiers for human activity recognition on connected devices.
Animals execute goal-directed behaviours despite the limited range and scope of their sensors. To cope, they explore environments and store memories maintaining estimates of important information that is not presently available. Recently, progress has been made with artificial intelligence (AI) agents that learn to per…
FinMem enhances LLM trading agents with layered memory and character design.
New memory allocation scheme improves image generation performance.
GPG improves RL from feedback with less memory and compute.
Unified framework supports lifelong learning properties.
Intense volatility in financial markets affect humans worldwide. Therefore, relatively accurate prediction of volatility is critical. We suggest that massive data sources resulting from human interaction with the Internet may offer a new perspective on the behavior of market participants in periods of large market move…
HTMRL uses HTM for RL, adapting faster to changing environments.
There is a consensus that human and non-human subjects experience temporal distortions in many stages of their perceptual and decision-making systems. Similarly, intertemporal choice research has shown that decision-makers undervalue future outcomes relative to immediate ones. Here we combine techniques from informatio…
Human activity recognition using smart home sensors is one of the bases of ubiquitous computing in smart environments and a topic undergoing intense research in the field of ambient assisted living. The increasingly large amount of data sets calls for machine learning methods. In this paper, we introduce a deep learnin…
A new algorithm improves recommendation systems by considering repeated exposure to actions.
DAM with MRL improves relational reasoning in MANNs.
X-DER improves continual learning by revising replay memory and learning unseen classes.
A new memory replay mechanism improves reinforcement learning stability and speed.
HMN detects fake faces using memory networks and visual cues.
In this work, we propose to learn a generative model using both learned features (through a latent space) and memories (through neighbors). Although human learning makes seamless use of both learned perceptual features and instance recall, current generative learning paradigms only make use of one of these two componen…
DRLViz interprets deep RL agent memory for better understanding.
Using raw sensor data to model and train networks for Human Activity Recognition can be used in many different applications, from fitness tracking to safety monitoring applications. These models can be easily extended to be trained with different data sources for increased accuracies or an extension of classifications …
SKVMN improves KT models by tracing student knowledge states and dependencies.
Deep neural networks (DNN) trained in a supervised way suffer from two known problems. First, the minima of the objective function used in learning correspond to data points (also known as rubbish examples or fooling images) that lack semantic similarity with the training data. Second, a clean input can be changed by a…
A novel memory network improves interpretability and training for EHR analysis.
In this paper we will try to assess the multifractality displayed by the high-frequency returns of Madrid's Stock Exchange IBEX35 index. A Multifractal Detrended Fluctuation Analysis shows that this index has a wide singularity spectrum which is most likely caused by its long memory. Our findings also show that this lo…
Machine learning improves learning and memory retention by optimizing study sessions.
Both the human brain and artificial learning agents operating in real-world or comparably complex environments are faced with the challenge of online model selection. In principle this challenge can be overcome: hierarchical Bayesian inference provides a principled method for model selection and it converges on the sam…
V-HMN integrates memory mechanisms for improved image recognition.
Consider unsupervised clustering of objects drawn from a discrete set, through the use of human intelligence available in crowdsourcing platforms. This paper defines and studies the problem of universal clustering using responses of crowd workers, without knowledge of worker reliability or task difficulty. We model sto…
The ability to look multiple times through a series of pose-adjusted glimpses is fundamental to human vision. This critical faculty allows us to understand highly complex visual scenes. Short term memory plays an integral role in aggregating the information obtained from these glimpses and informing our interpretation …
State of the art deep reinforcement learning algorithms take many millions of interactions to attain human-level performance. Humans, on the other hand, can very quickly exploit highly rewarding nuances of an environment upon first discovery. In the brain, such rapid learning is thought to depend on the hippocampus and…
Human categorization is one of the most important and successful targets of cognitive modeling in psychology, yet decades of development and assessment of competing models have been contingent on small sets of simple, artificial experimental stimuli. Here we extend this modeling paradigm to the domain of natural images…
Paper proposes DAC-ML, a cognitive architecture that learns quickly from few episodes.
With the breakthrough of computational power and deep neural networks, many areas that we haven't explore with various techniques that was researched rigorously in past is feasible. In this paper, we will walk through possible concepts to achieve robo-like trading or advising. In order to accomplish similar level of pe…
Machine reading using differentiable reasoning models has recently shown remarkable progress. In this context, End-to-End trainable Memory Networks, MemN2N, have demonstrated promising performance on simple natural language based reasoning tasks such as factual reasoning and basic deduction. However, other tasks, namel…
Hypothesis testing is an important cognitive process that supports human reasoning. In this paper, we introduce a computational hypothesis testing approach based on memory augmented neural networks. Our approach involves a hypothesis testing loop that reconsiders and progressively refines a previously formed hypothesis…
Human Activity Recognition (HAR) based on motion sensors has drawn a lot of attention over the last few years, since perceiving the human status enables context-aware applications to adapt their services on users' needs. However, motion sensor fusion and feature extraction have not reached their full potentials, remain…
Existing language models such as n-grams for software code often fail to capture a long context where dependent code elements scatter far apart. In this paper, we propose a novel approach to build a language model for software code to address this particular issue. Our language model, partly inspired by human memory, i…
Sparse Meta Networks adapt deep neural networks incrementally for fast learning.
Automated protein structure prediction from cryo-EM data.
Integrating visual and linguistic information into a single multimodal representation is an unsolved problem with wide-reaching applications to both natural language processing and computer vision. In this paper, we present a simple method to build multimodal representations by learning a language-to-vision mapping and…
Deep architecture learns transferable features for robust speech emotion recognition.
Deep learning model classifies concurrent human interactions from WiFi data with high accuracy.