A new neural network model improves reinforcement learning efficiency.
problem Improving sample efficiency in reinforcement learning.
method Proposes a neural network architecture using VQ-VAE and convolutional LSTM for world modeling.
result Shows comparable performance to SimPLe with significantly smaller model.
New model learns causal world dynamics from state space models.
problem Lack of causal world models in neural world modeling.
method State Space Models (SSM) with attention mechanisms.
result SSM can learn causal models of environments with equivalent performance.
This study applies EMD to MSCI World index and converts IMFs into graphs for GNN modeling.
problem Modeling financial time series with GNNs.
method EMD, CEEMDAN, graph transformations (natural visibility, horizontal visibility, recurrence, transition graphs), topological analysis.
result High-frequency IMFs yield dense, highly connected small-world graphs; low-frequency IMFs produce sparser networks.
The paper provides guidelines for choosing between SBI methods in complex biological models.
problem Choosing appropriate SBI methods for real-world biological data.
method Comprehensive guidelines and application to agent-based models.
result Statistical SBI methods outperform neural SBI methods with sufficient computational resources.
Neural approach enhances AI trustworthiness, generalization, and robustness.
problem Challenges in explaining, generalizing, and adapting AI models to uncertain environments.
method Customized trustworthy networks, flexible learning regularizers, open-world recognition losses.
result Significant performance improvements across various open-world multimedia recognition scenarios.
Predicting smartphone users location with WiFi fingerprints has been a popular research topic recently. In this work, we propose two novel deep learning-based models, the convolutional mixture density recurrent neural network and the VAE-based semi-supervised learning model. The convolutional mixture density recurrent …
The paper analyzes the training dynamics of neural networks using kernel methods.
problem Understanding the training dynamics of neural networks in high-dimensional settings.
method High-dimensional asymptotics and gradient flow on kernel least-squares objectives.
result The training dynamics of neural networks undergo three stages, characterized by behaviors in the Oracle and Empirical worlds.
Cosmos models scenes using neural encodings and symbolic attributes for compositional generalization.
problem Modeling scenes with high performance on unseen input scenes composed of known visual elements.
method Neurosymbolic grounding with neurosymbolic scene encodings and attention mechanisms.
result Establishes a new state-of-the-art for compositional generalization in world modeling.
We explore building generative neural network models of popular reinforcement learning environments. Our world model can be trained quickly in an unsupervised manner to learn a compressed spatial and temporal representation of the environment. By using features extracted from the world model as inputs to an agent, we c…
This paper describes our UNet based deep convolutional neural network approach on the Traffic4cast challenge 2019. Challenges task is to predict future traffic flow volume, heading and speed on high resolution whole city map. We used UNet based deep convolutional neural network to train predictive model for the short t…
A generative recurrent neural network is quickly trained in an unsupervised manner to model popular reinforcement learning environments through compressed spatio-temporal representations. The world model's extracted features are fed into compact and simple policies trained by evolution, achieving state of the art resul…
Deep neural networks are gaining increasing popularity for the classic text classification task, due to their strong expressive power and less requirement for feature engineering. Despite such attractiveness, neural text classification models suffer from the lack of training data in many real-world applications. Althou…
We propose a neural information processing system which is obtained by re-purposing the function of a biological neural circuit model, to govern simulated and real-world control tasks. Inspired by the structure of the nervous system of the soil-worm, C. elegans, we introduce Neuronal Circuit Policies (NCPs), defined as…
Neural network learns to solve Black-Scholes for stock options.
problem Stock option pricing using the Black-Scholes Equation.
method Neural Networks applied to solve the Black-Scholes Equation.
result Neural network can accurately forecast stock option prices.
This paper reviews methods to create compact neural networks for IoT applications.
problem Complex deep neural networks are costly and slow, hindering real-world deployment.
method Automatic synthesis of compact, accurate DNN/LSTM models.
result Compact neural networks reduce energy consumption, memory, and inference time.
We extend Neural Processes (NPs) to sequential data through Recurrent NPs or RNPs, a family of conditional state space models. RNPs model the state space with Neural Processes. Given time series observed on fast real-world time scales but containing slow long-term variabilities, RNPs may derive appropriate slow latent …
Transformer learns long-term dependencies from real-world data.
problem Sample inefficiency in deep reinforcement learning.
method Transformer architecture applied to autoregressive real-world episodes.
result Transformer-based world model generates meaningful experience.
LMoE uses LLMs to improve stock trading by selecting experts based on textual and price data.
problem Traditional neural network-based router selection in MoE models is suboptimal and ignores textual data.
method Proposes LLMoE, using LLMs as routers to select experts based on historical price data and stock news.
result LLoM outperforms state-of-the-art MoE models and other deep neural network approaches.
Deep Neural Networks (DNNs) are usually over-parameterized, causing excessive memory and interconnection cost on the hardware platform. Existing pruning approaches remove secondary parameters at the end of training to reduce the model size; but without exploiting the intrinsic network property, they still require the f…
We propose a neural architecture with the main characteristics of the most successful neural models of the last years: bidirectional RNNs, encoder-decoder, and the Transformer model. Evaluation on three sequence labelling tasks yields results that are close to the state-of-the-art for all tasks and better than it for s…
Understanding the 3-dimensional structure of the world is a core challenge in computer vision and robotics. Neural rendering approaches learn an implicit 3D model by predicting what a camera would see from an arbitrary viewpoint. We extend existing neural rendering to more complex, higher dimensional scenes than previo…
NPGNN improves graph link prediction by adapting to new graphs.
problem Inductive link prediction in graphs with limited training data.
method Meta-learning with graph neural networks (NPGNN).
result NPGNN outperforms state-of-the-art models in real-world graphs.
Physics-informed neural networks improve model accuracy and efficiency.
problem Accurate dynamic models for technical systems are hard to achieve.
method Physics-informed neural ordinary differential equations (PINODE) integrating Lagrangian mechanics.
result Hybrid model combines physical insight and data approximation.
Graph neural network explainer identifies causal subgraphs ensuring predictions.
problem Spurious correlations in GNN explainers.
method Proposes {
ame}, a GNN causal explainer via causal inference.
result Significantly outperforms existing GNN explainers in exact groundtruth explanation identification.
Neural model accelerates SDDP for stochastic optimization.
problem Exponential complexity of SDDP limits its applicability to low-dimensional problems.
method Trainable neural model maps problem instances to a low-dimensional piecewise linear value function.
result ν-SDDP significantly reduces problem solving cost without sacrificing solution quality.
Myriad offers a testbed for integrating machine learning and trajectory optimization.
problem Real-world trajectory optimization challenges.
method JAX-based testbed with machine learning and trajectory optimization integration.
result End-to-end learning and planning with neural ODEs.
Combines neural networks with SDEs for robust pricing and hedging.
problem Inadequate financial models lead to undetected and unquantifiable risks.
method Neural SDEs integrating machine learning and classical SDEs.
result Robust bounds for derivative prices and hedging strategies.
We derive a novel sensitivity analysis of input variables for predictive epistemic and aleatoric uncertainty. We use Bayesian neural networks with latent variables as a model class and illustrate the usefulness of our sensitivity analysis on real-world datasets. Our method increases the interpretability of complex blac…
Novel neural likelihood ratio estimation for negative data in particle physics.
problem Estimating likelihood ratios with negative probability densities and weights.
method Introducing a novel loss function and a new model architecture based on signed mixture models.
result Demonstrated improved estimation on a real-world example from particle physics.
EvoNet predicts the evolution of dynamic graphs using a graph neural network and recurrent architecture.
problem Predicting the evolution of dynamic graphs is challenging and underexplored.
method EvoNet uses a graph neural network and recurrent architecture to predict the evolution of dynamic graphs.
result EvoNet effectively predicts the evolution of dynamic graphs on both artificial and real-world datasets.
CaTs use DAGs with transformers to enforce causal constraints, improving neural network robustness.
problem Neural networks lack inherent causal structure respect, leading to reliability issues.
method Introducing Causal Transformers (CaTs) that operate under predefined causal constraints specified by DAGs.
result CaTs improve robustness and interpretability of neural networks under causal constraints.
Study introduces a benchmark suite for evaluating neural MI estimators on real-world unstructured datasets.
problem Lack of comprehensive evaluation methods for neural MI estimators on real-world unstructured datasets.
method Developed a benchmark suite using same-class sampling and a binary symmetric channel trick.
result Showed accurate manipulation of true MI values of real-world datasets.
This work improves deep neural network probability estimation methods.
problem Estimating probabilities from high-dimensional data with inherent uncertainty.
method Investigates and compares methods for probability estimation using deep neural networks, proposing a new method that promotes consistent probabilities.
result The new method outperforms existing approaches on most metrics on simulated and real-world data.
Develops approximately equivariant neural processes for better data modeling.
problem Real-world data often breaks exact equivariance; how to model this?
method General approach to creating approximately equivariant architectures, applicable to any model and symmetry group.
result Approximately equivariant neural processes outperform non-equivariant and strictly equivariant models in regression tasks.
Neural networks are becoming a popular tool for solving many real-world problems such as object recognition and machine translation, thanks to its exceptional performance as an end-to-end solution. However, neural networks are complex black-box models, which hinders humans from interpreting and consequently trusting th…
Survey on uncertainty in GNNs for improved model reliability.
problem Inherent randomness and model training errors lead to unstable GNN predictions.
method Comprehensive overview of GNN uncertainty theory and methods.
result Integration of uncertainty in GNNs enhances model performance and reliability.
This work bridges continual learning, active learning, and open set recognition in deep neural networks.
problem Protecting previously acquired representations from catastrophic forgetting in deep neural networks.
method Surveying the literature and proposing a consolidated view to integrate open set recognition and active learning principles.
result Joint improvement in alleviating catastrophic forgetting, querying data, selecting task orders, and robust open world application.
POLA adapts learning rates for online time series prediction.
problem Adapting to changing data distributions in dynamic environments.
method Adaptive learning rate regulation for recurrent neural networks.
result POLA outperforms other online prediction methods in real-world datasets.
Recurrent neural networks (RNNs) have been extraordinarily successful for prediction with sequential data. To tackle highly variable and noisy real-world data, we introduce Particle Filter Recurrent Neural Networks (PF-RNNs), a new RNN family that explicitly models uncertainty in its internal structure: while an RNN re…
Method learns conditional distributions using neural entropic optimal transport.
problem Challenges in learning multiple conditional distributions.
method Neural entropic optimal transport method with two networks and regularization.
result Effective learning of conditional distributions with limited samples.
CoMGNN models heterogeneous graphs with evolving nodes and edges.
problem Modeling complex, evolving graphs with diverse information.
method Meta graph attention on co-evolving heterogeneous graphs.
result Significant improvement over state-of-the-art methods.
Graphs are essential representations of many real-world data such as social networks. Recent years have witnessed the increasing efforts made to extend the neural network models to graph-structured data. These methods, which are usually known as the graph neural networks, have been applied to advance many graphs relate…
The article explores how organisms and machines learn and recognize the world using Bayesian inference and thermodynamics.
problem Understanding how organisms and machines learn and recognize the world.
method Introducing a thermodynamic view of the Bayesian brain hypothesis, using a simple generative model of spiking neural populations.
result The process of Bayesian inference can be quantified using entropy, revealing the perceptual capacity of neural activity.
As humans we are driven by a strong desire for seeking novelty in our world. Also upon observing a novel pattern we are capable of refining our understanding of the world based on the new information---humans can discover their world. The outstanding ability of the human mind for discovery has led to many breakthroughs…
Adversarial attacks can fool ML energy theft detection models.
problem Vulnerability of ML-based energy theft detection models to adversarial attacks.
method Design of an adversarial measurement generation algorithm.
result ML models can be significantly fooled by adversarial attacks, reducing their detection accuracy.
Random matrix theory predicts neural representations generalize well.
problem Understanding why neural representations generalize well in practice.
method Applied random matrix theory to kernel regression and neural networks.
result GCV estimator accurately predicts generalization risk in overparameterized settings.
We present MILABOT: a deep reinforcement learning chatbot developed by the Montreal Institute for Learning Algorithms (MILA) for the Amazon Alexa Prize competition. MILABOT is capable of conversing with humans on popular small talk topics through both speech and text. The system consists of an ensemble of natural langu…
This review compares GAMs and neural networks on real-world tabular data.
problem Comparing the performance and characteristics of GAMs and neural networks in tabular data applications.
method Systematic review following PRISMA guidelines, extracting and analysing key attributes from 143 papers and 430 datasets.
result No consistent evidence of superiority for either GAMs or neural networks, with performance trade-offs depending on dataset characteristics.