Improves deep learning robustness by considering task and model.
problem Adversarial attacks on deep learning systems.
method Binary and interval label encoding strategy to redefine classification tasks and design corresponding loss functions.
result Our method enhances robustness without sacrificing accuracy.
Paper explores physics-informed deep learning for system reliability assessment.
problem Limited study on deep learning for system reliability assessment.
method Physics-informed deep learning approach for system reliability assessment.
result Physics-informed deep learning can alleviate computational challenges and combine measurement data and mathematical models.
Deep learning networks are approximated using dynamical systems theory.
problem Understanding the approximation capabilities of deep learning networks.
method Modeling deep residual networks as continuous-time dynamical systems and using approximation theories in Lp. result Established general sufficient conditions for universal approximation of deep residual networks.
How to understand deep learning systems remains an open problem. In this paper we propose that the answer may lie in the geometrization of deep networks. Geometrization is a bridge to connect physics, geometry, deep network and quantum computation and this may result in a new scheme to reveal the rule of the physical w…
Deep SSMs use neural networks to identify complex systems.
problem Identifying nonlinear systems with high uncertainty.
method Deep state space models with neural networks.
result Deep SSMs outperform traditional methods on benchmarks.
Survey of deep learning methods for recommender systems challenges.
problem Cold start and candidate generation challenges in recommender systems.
method Taxonomy of deep learning techniques addressing cold start and candidate generation problems.
result Taxonomy of deep learning techniques to address recommender systems challenges.
Stable deep models learn dynamical systems with formal stability guarantees.
problem Difficulties in making formal claims about stability of deep network dynamics models.
method Jointly learning a dynamics model and Lyapunov function to ensure non-expansiveness.
result Proposes an approach for stable deep learning of dynamical systems.
Deep learning improves conversational recommender systems.
problem Creating effective goal-oriented dialogue systems through natural language interactions.
method Apply deep learning techniques to conversational recommender systems.
result Deep learning models enhance user preference learning in CRS.
Deep learning models learn chaotic system dynamics from real and simulated data.
problem Training deep learning models for chaotic systems requires big data.
method Jointly train deep neural networks on real and simulated data, enforcing physical laws.
result Proposes knowledge-based deep learning (KDL) for accurate forecasting of chaotic systems.
Proposes a deep latent factor model for better recommendation systems.
problem Improving collaborative filtering in recommendation systems.
method Introduces a deeper latent factor model using deep learning.
result Significantly outperforms state-of-the-art techniques in experiments.
Proposes a deep hybrid model for better recommendation systems.
problem Limited studies on hybrid recommender systems and the need for more advanced approaches.
method Integrates deep learning with ID embeddings and auxiliary features for improved recommendation.
result Improves recommendation results over deep learning models using ID embeddings.
Deep learning's convolutional networks improve system identification.
problem Nonlinear system identification problems.
method Exploration of relationships between TCN and Volterra series/block-oriented models.
result TCN outperforms traditional models in sequence modeling tasks.
In this paper, a new deep reinforcement learning based augmented general sequence tagging system is proposed. The new system contains two parts: a deep neural network (DNN) based sequence tagging model and a deep reinforcement learning (DRL) based augmented tagger. The augmented tagger helps improve system performance …
Model-based machine learning improves communication systems.
problem Improving symbol detection in communication receivers.
method Review and comparison of model-based and deep learning approaches, focusing on deep unfolding and DNN-aided hybrid algorithms.
result Different strategies of conventional deep architectures and hybrid algorithms show advantages and drawbacks.
Deep RL optimizes power control for wireless multicast systems.
problem Optimal power control is intractable due to a large state space.
method Deep reinforcement learning with function approximation via neural networks.
result Optimal power control can be learned for large systems.
Paper tackles interpretability issues in deep learning models.
problem Lack of understanding of deep learning models' decision-making processes.
method Integrates concepts from machine learning, quantum computation, and quantum field theory.
result Demonstrates a many valued quantum logic system in Convolutional Deep Belief Networks.
Survey of deep RL in intelligent transportation systems.
problem Optimizing traffic signals and autonomous driving using deep RL.
method Comprehensive review of deep RL applications in traffic control and autonomous driving.
result Summarizes existing works in deep RL-based transportation applications.
Physics-guided model improves deep learning for nonlinear systems.
problem Intractable inference of nonlinear dynamical systems from data.
method Physics-guided Deep Markov Model (PgDMM) using neural networks.
result Improved performance on nonlinear systems with structured latent space.
Why and how that deep learning works well on different tasks remains a mystery from a theoretical perspective. In this paper we draw a geometric picture of the deep learning system by finding its analogies with two existing geometric structures, the geometry of quantum computations and the geometry of the diffeomorphic…
Deep learning methods are reviewed for preserving structure in neural networks.
problem Challenges in applying deep learning, especially in preserving structure.
method Review of existing deep learning methods and new algorithmic frameworks.
result Mathematical understanding and systematic design of deep learning methods to preserve structure.
Paper uses deep learning for systemic risk measures.
problem Computing optimal capital allocations for systemic risk.
method Deep learning algorithms to solve primal and dual problems.
result Deep learning provides fair risk allocations.
The discovery of adversarial examples has raised concerns about the practical deployment of deep learning systems. In this paper, we demonstrate that adversarial examples are capable of manipulating deep learning systems across three clinical domains. For each of our representative medical deep learning classifiers, bo…
Unified deep learning theory via dynamical systems and optimal control.
problem Lack of a unified framework in deep learning theory.
method Viewing deep neural networks as discrete-time nonlinear dynamical systems and optimization algorithms as controllers.
result Revealed convergence and generalization properties of training processes.
Paper uses deep learning to compute committor functions for rare events in complex systems.
problem Computing committor functions for low-temperature, high-dimensional systems is challenging.
method Combines deep learning, data sampling, and feature engineering.
result Achieves good performance on complex benchmark problems with rough energy landscapes.
Orpheus simplifies deep learning deployment on edge devices.
problem Optimizing deep learning inference on edge devices for efficiency.
method Orpheus is a new framework with a small codebase, minimal dependencies, and easy integration.
result Preliminary results show the effectiveness of Orpheus for inference optimisations.
We explore the use of deep learning and deep reinforcement learning for optimization problems in transportation. Many transportation system analysis tasks are formulated as an optimization problem - such as optimal control problems in intelligent transportation systems and long term urban planning. Often transportation…
Autonomous AI systems will be entering human society in the near future to provide services and work alongside humans. For those systems to be accepted and trusted, the users should be able to understand the reasoning process of the system, i.e. the system should be transparent. System transparency enables humans to fo…
Deep learning system generates new Chinese fonts via style variables.
problem Efficiently design new Chinese fonts.
method End-to-end deep learning system generating new style fonts via interpolation of latent style-related embedding variables.
result Smooth transition between different font styles achieved.
Method learns latent dynamics of complex systems from noisy data.
problem Challenging to construct ROMs from noisy high-dimensional data.
method Recurrent stochastic variational deep kernel learning (SVDKL).
result Framework accurately predicts system evolution in low-dimensional latent spaces.
Paper introduces timing-based adversarial attacks on DRL-based navigation systems.
problem Vulnerability of DRL-based navigation systems to adversarial attacks.
method Timing-based adversarial strategies using physical noise patterns.
result Adversarial timing attacks significantly degrade DRL-based navigation performance.
The problem of state estimation for unobservable distribution systems is considered. A deep learning approach to Bayesian state estimation is proposed for real-time applications. The proposed technique consists of distribution learning of stochastic power injection, a Monte Carlo technique for the training of a deep ne…
Deep learning improves solving medical imaging problems with sparse data.
problem Solving underdetermined inverse problems in medical imaging.
method Analyzing the structure of training data suitable for deep learning to solve highly non-linear underdetermined systems.
result Deep learning can learn reconstruction maps from training data for highly underdetermined systems.
DeepRSCN models nonlinear systems using stochastic configurations.
problem Modeling nonlinear dynamic systems efficiently.
method Incrementally constructed deep reservoir computing framework with random parameters and online weight updates.
result DeepRSCN outperforms single-layer networks in efficiency, learning, and generalization.
Deep-PrAE improves rare-event simulation for black-box systems.
problem Evaluating rare safety-critical events in learning-based systems.
method Combines deep neural networks with IS to create statistically guaranteed estimations.
result Deep-PrAE provides accurate bounds on safety-critical event probabilities.
A new recommendation method combining deep learning and graph analysis improves performance.
problem Challenges in recommender systems like cold-start and sparsity.
method Matrix Factorization, deep Autoencoders, and deep embedding methods.
result The proposed method outperforms existing state-of-the-art methods.
Deep reinforcement learning finds optimal learning policies for adaptive systems.
problem Finding individualized learning plans for learners with unknown latent traits.
method Formulated as a Markov decision process, applied deep Q-learning with a transition model estimator.
result The algorithm efficiently discovers optimal learning policies with small data sets.
Research proposes a test case generation system for deep learning models using dataset properties.
problem Automated generation of extensive test cases for deep learning models is challenging.
method Measures dataset quality and proposes a test case generation system guided by dataset properties.
result Systematic test case generation for deep learning models is effective.
DeepFair improves fairness in recommender systems without sacrificing accuracy.
problem Lack of bias management in recommender systems leads to unfair recommendations for minority groups.
method Deep Learning based Collaborative Filtering algorithm that balances fairness and accuracy.
result It is possible to make fair recommendations without losing significant accuracy.
Can we manipulate multiple deep neural networks simultaneously?
problem Selective fooling of multiple machine learning systems.
method Formulated as a novel optimization problem.
result It is easy to selectively manipulate multiple MNIST classifiers simultaneously.
Modeling dynamical systems is important in many disciplines, e.g., control, robotics, or neurotechnology. Commonly the state of these systems is not directly observed, but only available through noisy and potentially high-dimensional observations. In these cases, system identification, i.e., finding the measurement map…
This work explores using deep NNs to learn quantum systems from probability distributions.
problem Learning quantum systems from limited probability distribution data.
method Using deep neural networks to reconstruct quantum Hamiltonian from probability distributions.
result Deep neural networks can learn quantum Hamiltonians from probability distributions.
Study on deep learning IDS resistance against adversarial attacks.
problem Vulnerabilities in deep learning-based IDS against adversarial attacks.
method Apply min-max optimization to train IDS against adversarial samples.
result Adversarial attack methods can be used in continuous domains and boost IDS robustness.
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…
Paper proposes a GPU-based system for training massive deep learning models in ads systems.
problem Training massive deep learning models with terabyte-scale parameters in ads systems.
method Hierarchical GPU parameter server with 3-layer storage (GPU High-Bandwidth Memory, CPU main memory, SSD).
result 4-node hierarchical GPU parameter server trains a model 2X faster than a 150-node in-memory system.
Deep active learning improves solvability prediction in power systems.
problem Inconclusive conservatism in traditional solvability region analysis methods.
method Proposes a deep active learning framework to reduce labeled dataset size.
result Significantly reduces the size of labeled dataset for training.
Automated testing improves deep learning model accuracy by 259.2%.
problem Ensuring robustness of deep learning models through automated testing.
method Jointly optimizing differential behaviors and neuron coverage; generating corner-cases; applying transformations and GANs.
result Deep learning model accuracy increased by 259.2% using automated generated corner cases.
Deep learning detects arrhythmia from RR-interval ECG data.
problem Diagnosing arrhythmia using ECG data.
method Convolutional neural network (CNN) on time-sliced RR-interval data.
result Compact system achieves accurate arrhythmia detection.
Deep Lagrangian Networks learn physics for robust control with fewer samples.
problem Learning physics models for model-based control requires robust extrapolation from limited samples.
method Imposing Lagrangian Mechanics on a deep network structure (DeLaN).
result DeLaN outperforms previous methods at learning speed and robust extrapolation.