Investigates how neural network graph structure impacts predictive performance.
problem Lack of understanding between neural network graph structure and predictive performance.
method Developed relational graph representation to analyze neural networks, identifying a 'sweet spot' for improved performance.
result Identified a 'sweet spot' in relational graph structure that significantly improves neural network predictive performance.
Quantum neural network and tensor network models outperform classical models in Japanese stock market predictions.
problem Improving stock return predictions using quantum and quantum-inspired machine learning.
method Evaluation of quantum neural network and tensor network models against classical models like linear and neural networks.
result Tensor network model outperforms classical models in Japanese stock market, including linear and neural network models.
A new design methodology for neural networks that is guided by traditional algorithm design is presented. To prove our point, we present two heuristics and demonstrate an algorithmic technique for incorporating additional weights in their signal-flow graphs. We show that with training the performance of these networks …
Study analyzes Echo State Network parameters for Rossler attractor dynamics.
problem Understanding the influence of network type on Echo State Network performance.
method Experimental analysis of Echo State Network parameters using Rossler attractor.
result Exploration of how network type affects Echo State Network performance.
A method to analyze neural network performance by measuring layer saturation.
problem Understanding which layers contribute to network performance.
method Layer saturation method: restricts layer output to eigenspace of variance matrix.
result Layer saturation indicates which layers contribute to network performance.
This work investigates the framework and performance issues of the composite neural network, which is composed of a collection of pre-trained and non-instantiated neural network models connected as a rooted directed acyclic graph for solving complicated applications. A pre-trained neural network model is generally well…
This study explores training Bayesian neural networks at scale using high-performance computing.
problem Challenges in training Bayesian neural networks at scale due to computational overhead.
method High-performance computing with distributed training, network pruning.
result Pruning up to 80% of the network can reduce inference time by 7.0% without significant accuracy loss.
The recent advent of `Internet of Things' (IOT) has increased the demand for enabling AI-based edge computing. This has necessitated the search for efficient implementations of neural networks in terms of both computations and storage. Although extreme quantization has proven to be a powerful tool to achieve significan…
Network degeneracy affects training performance, especially in deep networks.
problem Degeneracy in deep neural networks leads to poor training performance.
method Predicted degeneracy level correlates with training dynamics using finite and infinite width networks.
result Degeneracy in neural networks correlates with training performance and can be predicted.
The quest for performant networks has been a significant force that drives the advancements of deep learning in recent years. While rewarding, improving network design has never been an easy journey. The large design space combined with the tremendous cost required for network training poses a major obstacle to this en…
New method finds sparse networks without labels, improving performance.
problem Sparse connectivity in neural networks to reduce memory and energy demands.
method Neural Tangent Transfer method to find sparse networks without labels.
result Sparse networks achieve higher classification performance and faster convergence.
Study evaluates neural networks based on random graph structures and finds key performance indicators.
problem Understanding and optimizing neural network architectures using graph theory.
method Evaluation of neural networks with random graph structures, focusing on structural and numerical properties.
result A new numerical graph characteristic selects a set of quasi-1-dimensional graphs that perform well.
Bayesian neural networks show good correlation between out-of-sample performance and Bayesian evidence.
problem Improving the out-of-sample performance of Bayesian neural networks.
method Numerical sampling of Bayesian posterior, ensembling over architectures, analysis of evidence vs. model size.
result Good correlation between out-of-sample performance and Bayesian evidence; ensembling improves performance.
A powerful network teaches a weak one, improving its performance.
problem Improving the performance of a weak neural network using a more powerful one.
method During training, a weak network learns features from a strong network to minimize feature distance.
result A weak neural network can increase its performance by learning from a more powerful network.
Randomly initialized networks contain subnetworks that perform similarly to target networks.
problem Proving the lottery ticket hypothesis for neural networks.
method Pruning over-parameterized neural networks to find subnetworks.
result Randomly initialized networks contain subnetworks with similar performance to target networks without additional training.
Stochastic models analyze traffic network performance.
problem Evaluate traffic system performance.
method Stochastic cell transmission models, preference functionals, Gaussian process regression.
result Illustrated in two case studies.
Paper proposes ECOC for deep neural network ensembles to improve performance.
problem Designing an ensemble of deep networks is time-consuming and often not beneficial.
method ECOC framework applied to deep networks, with design strategies to balance accuracy and complexity.
result Proposed combinatory technique achieves highest classification performance.
Trained recurrent networks are powerful tools for modeling dynamic neural computations. We present a target-based method for modifying the full connectivity matrix of a recurrent network to train it to perform tasks involving temporally complex input/output transformations. The method introduces a second network during…
The task of accelerating large neural networks on general purpose hardware has, in recent years, prompted the use of channel pruning to reduce network size. However, the efficacy of pruning based approaches has since been called into question. In this paper, we turn to distillation for model compression---specifically,…
Paper benchmarks quantum neural networks against classical ones for binary classification tasks.
problem Comparing quantum neural networks with classical ones for binary classification.
method Evaluated with two toy examples, focusing on model complexity and training data size.
result EQNN and QNN outperform ENN and DNN for smaller parameter sets and training data samples.
FIRE PBT improves neural network training by focusing on long-term performance.
problem Greedy decision mechanisms in PBT lead to poor long-term performance.
method FIRE PBT uses a fitness metric to encourage long-term performance over short-term improvements.
result FIRE PBT outperforms PBT on ImageNet and matches hand-tuned learning rates.
Not all neural network architectures are created equal, some perform much better than others for certain tasks. But how important are the weight parameters of a neural network compared to its architecture? In this work, we question to what extent neural network architectures alone, without learning any weight parameter…
Improved neural network convergence with causal Bayesian modeling in retail performance.
problem Improving neural network convergence in retail performance models.
method Causal Bayesian neural network implementation, removal of weakest SEM path, Flipout layers, Vadam optimizer.
result Neural network convergence improved with removal of the weakest SEM path.
Fully convolutional neural networks (FCN) have been shown to achieve state-of-the-art performance on the task of classifying time series sequences. We propose the augmentation of fully convolutional networks with long short term memory recurrent neural network (LSTM RNN) sub-modules for time series classification. Our …
Invariant polynomials improve machine learning performance.
problem Improving machine learning algorithms using invariant polynomials.
method Developed and implemented Lorentz- and permutation-invariant polynomial generators in neural networks.
result Reduction in loss on training and validation data with Hironaka decompositions.
Protein function prediction is the important problem in modern biology. In this paper, the un-normalized, symmetric normalized, and random walk graph Laplacian based semi-supervised learning methods will be applied to the integrated network combined from multiple networks to predict the functions of all yeast proteins …
This work theoretically investigates the performance of a composite neural network. A composite neural network is a rooted directed acyclic graph combining a set of pre-trained and non-instantiated neural network models, where a pre-trained neural network model is well-crafted for a specific task and targeted to approx…
Bayesian sparsification improves complex-valued neural networks by 50-100x with minimal performance loss.
problem Efficiently compressing complex-valued neural networks for embedded systems.
method Extending Sparse Variational Dropout to complex-valued networks and conducting a numerical study.
result Achieved state-of-the-art performance on MusicNet with 50-100x compression.
This paper shows RBMs can maintain strong performance even after extreme pruning, but only if done early in training.
problem The computational and environmental costs of large neural networks.
method Investigating the performance of RBMs under extreme pruning conditions, inspired by the Lottery Ticket Hypothesis.
result RBMs can achieve high-quality generative performance even after 80% pruning, but performance degrades sharply above a critical point.
FrostNet improves INT8 quantization efficiency in mobile networks.
problem The importance of network architecture for optimal INT8 quantization.
method Quantization-aware training (QAT) with StatAssist and GradBoost, hardware-aware NAS.
result FrostNets achieve higher recognition accuracy with comparable latency when quantized.
Paper optimizes neural network initialization using SMT solvers.
problem Improving neural network performance through better initialization.
method Reduces initialization to SMT problem solving.
result Proposed method achieves better performance than random initialization.
We propose a new scalable method to optimize the architecture of an artificial neural network. The proposed algorithm, called Greedy Search for Neural Network Architecture, aims to determine a neural network with minimal number of layers that is at least as performant as neural networks of the same structure identified…
In recent years an increasing number of researchers and practitioners have been suggesting algorithms for large-scale neural network architecture search: genetic algorithms, reinforcement learning, learning curve extrapolation, and accuracy predictors. None of them, however, demonstrated high-performance without traini…
Improves neural network performance by enriching training dataset.
problem Achieving worst-case performance guarantees in neural networks.
method Adapting training dataset during training to reduce worst-case violations.
result Improved worst-case performance guarantees in neural networks.
Predicting neural network accuracy from weights without testing.
problem Predicting neural network performance based on weights alone.
method Used simple statistics of weights to rank neural networks' performance.
result Simple predictors can rank networks' performance with high accuracy (R2 score > 0.98).
Fine-tuning neural networks to guarantee performance on specific examples can also introduce incorrect inputs.
problem Ensuring reliable performance of neural networks on specific examples.
method Using SMT solvers to fine-tune ReLU neural networks to guarantee outcomes on a finite set of particular examples.
result Fine-tuning can introduce incorrect inputs that trigger unexpected performance.
Neural networks outperform kernel methods in classifying high-dimensional Gaussian mixtures.
problem Classifying high-dimensional Gaussian mixtures using kernel methods and neural networks.
method Theoretical analysis and derivation of learning dynamics for 2LNN and comparison with kernel methods.
result 2LNN can achieve near-optimal performance on high-dimensional Gaussian mixture classification tasks, surpassing kernel methods.
This paper investigates the anti-jamming performance of a cognitive radar under a partially observable Markov decision process (POMDP) model. First, we obtain an explicit expression for uncertainty of jammer dynamics, which paves the way for illuminating the performance metric of probability of being jammed for the rad…
Unified scaling laws reveal how model size and training time impact neural network performance.
problem Understanding how much performance improvement can be expected from scaling model size or data volume.
method Established scale-time equivalence and combined it with a linear model analysis of double descent.
result Unified theoretical scaling laws explain previously unexplained phenomena and offer a more accessible path to training large models.
Gradient amplification boosts deep learning model performance without increasing training time.
problem Vanishing gradients in deep neural networks.
method Gradient amplification approach to prevent vanishing gradients and training strategy to enable/disable across epochs.
result Improves performance of deep learning models with reduced training time.
Proposes TAGI for efficient Gaussian inference in Bayesian neural networks.
problem Efficient inference in Bayesian neural networks with complex architectures.
method Analytical method for tractable approximate Gaussian inference (TAGI).
result Matches performance of gradient-based methods with O(n) computational complexity. This paper introduces a new method for neural networks that doesn't need a global coordinate system.
problem The lack of a global coordinate system in neural networks limits their performance and explainability.
method Proposes a learnable topological layer that works in a general metric space (Hilbert space) without requiring a Euclidean space.
result The proposed method eliminates the need for a costly parametrization stage and achieves optimal network performance.
In-network learning outperforms Federated and Split learning in wireless networks.
problem Efficiently using distributed features for inference in wireless networks.
method Proposes 'in-network learning' architecture, uses neural networks for optimization, compares with Federated and Split learning.
result In-network learning offers better accuracy and bandwidth savings.
New neural networks combine additive regression with traditional architectures.
problem Performance limitations and high parameter requirements of traditional neural networks.
method Introduce hybrid deep additive neural networks with simpler activation and basis functions.
result Hybrid neural networks achieve better performance with fewer parameters.
Evolutionary algorithms improve neural network performance by discovering better activation functions.
problem The choice of activation function affects neural network performance, but ReLU remains dominant.
method Defined a tree-based search space of candidate activation functions and used evolutionary algorithms (mutation, crossover, exhaustive search) to explore and discover better functions.
result Replacing ReLU with evolved activation functions statistically significantly increases network accuracy.
Study reveals biases in gradient descent for GLNs, improving neural network performance.
problem Understanding and improving the inductive biases of deep neural networks.
method Derive infinite-time training limit of gated linear networks and generalize to other networks.
result Theoretical framework captures key inductive biases of ReLU networks.
There is emerging interest in performing regression between distributions. In contrast to prediction on single instances, these machine learning methods can be useful for population-based studies or on problems that are inherently statistical in nature. The recently proposed distribution regression network (DRN) has sh…
We study the problem of identifying different behaviors occurring in different parts of a large heterogenous network. We zoom in to the network using lenses of different sizes to capture the local structure of the network. These network signatures are then weighted to provide a set of predicted labels for every node. W…