arXiv research

Fault-tolerant neural networks inspired by biological error correction codes.

Khovanov homology helps create quantum error-correcting codes.

Quantum codes on hyperbolic lattices outperform Euclidean ones with higher rates and lower overhead.

New invariant for prime alternating knots from error-correcting codes

The paper relaxes constraints on predictive coding models, making them more biologically plausible.

We propose rectified factor networks (RFNs) to efficiently construct very sparse, non-linear, high-dimensional representations of the input. RFN models identify rare and small events in the input, have a low interference between code units, have a small reconstruction error, and explain the data covariance structure. R…

Using 4-dimensional arithmetic hyperbolic manifolds, we construct some new homological quantum error correcting codes. They are LDPC codes with linear rate and distance $n^ε$. Their rate is evaluated via Euler characteristic arguments and their distance using $\mathbb{Z}_2$-systolic geometry. This construction answers …

Generative AI decodes quantum codes without labeled data.

CodNN uses error-correcting codes to make neural networks more resilient to noise.

This paper proposes a novel deep learning-based error correction coding scheme for AWGN channels under the constraint of one-bit quantization in the receivers. Specifically, it is first shown that the optimum error correction code that minimizes the probability of bit error can be obtained by perfectly training a speci…

A model corrects Lithuanian grammatical errors.

Finding optimal correction of errors in generic stabilizer codes is a computationally hard problem, even for simple noise models. While this task can be simplified for codes with some structure, such as topological stabilizer codes, developing good and efficient decoders still remains a challenge. In our work, we syste…

New model reveals balance crucial for robust neural coding.

Paper designs optimal ECOCs using IP for robust multiclass classification.

Quantum codes linked to abelian varieties, providing mathematical rigor.

Finding biologically plausible alternatives to back-propagation of errors is a fundamentally important challenge in artificial neural network research. In this paper, we propose a learning algorithm called error-driven Local Representation Alignment (LRA-E), which has strong connections to predictive coding, a theory t…

Paper proposes IABF to improve NECST robustness.

After being trained, classifiers must often operate on data that has been corrupted by noise. In this paper, we consider the impact of such noise on the features of binary classifiers. Inspired by tools for classifier robustness, we introduce the same classification probability (SCP) to measure the resulting distortion…

We propose a novel neural sequence prediction method based on \textit{error-correcting output codes} that avoids exact softmax normalization and allows for a tradeoff between speed and performance. Instead of minimizing measures between the predicted probability distribution and true distribution, we use error-correcti…

We use Khovanov homology to define families of LDPC quantum error-correcting codes: unknot codes with asymptotical parameters [[3^(2l+1)/sqrt(8πl);1;2^l]]; unlink codes with asymptotical parameters [[sqrt(2/2πl)6^l;2^l;2^l]] and (2,l)-torus link codes with asymptotical parameters [[n;1;d_n]] where d_n>\sqrt(n)/1.62.

Predictive coding networks are shown to be stable, robust, and converge faster than backpropagation.

New algorithm for multi-player bandits with collision-dependent rewards.

We introduce a differential geometric framework for describing families of quantum error-correcting codes and for understanding quantum fault tolerance. This work unifies the notion of topological fault tolerance with fault tolerance in other kinds of quantum error-correcting codes. In particular, we use fibre bundles …

Finding efficient decoders for quantum error correcting codes adapted to realistic experimental noise in fault-tolerant devices represents a significant challenge. In this paper we introduce several decoding algorithms complemented by deep neural decoders and apply them to analyze several fault-tolerant error correctio…

Optimal algorithm selects biological models without prior info.

Researchers found the maximum number of holes in polyominoes grows proportionally to the dimension.

SCaSML improves PDE solvers by correcting errors efficiently.

A new algorithm reduces regret in multi-player bandits without collision info.

Spatial separation of suspended particles based on contrast in their physical or chemical properties forms the basis of various biological assays performed on lab-on-achip devices. To electronically acquire this information, we have recently introduced a microfluidic sensing platform, called Microfluidic CODES, which c…

In my masters thesis I prove a square root bound on the distance of homological codes that come from two dimensional surfaces, as a result of the systolic inequality. I also give a detailed version of M.H. Freedman's proof that due to systolic freedom, this bound does not hold in higher dimensions.

Improved error correction using neural networks and belief propagation.

Deep learning algorithms for connectomics rely upon localized classification, rather than overall morphology. This leads to a high incidence of erroneously merged objects. Humans, by contrast, can easily detect such errors by acquiring intuition for the correct morphology of objects. Biological neurons have complicated…

Study of manifolds with prime cyclic group actions and curvature properties.

Though deep learning has been applied successfully in many scenarios, malicious inputs with human-imperceptible perturbations can make it vulnerable in real applications. This paper proposes an error-correcting neural network (ECNN) that combines a set of binary classifiers to combat adversarial examples in the multi-c…

A new model for sequential memory using temporal predictive coding.

Supervised training of neural networks for classification is typically performed with a global loss function. The loss function provides a gradient for the output layer, and this gradient is back-propagated to hidden layers to dictate an update direction for the weights. An alternative approach is to train the network …

Proposes a guaranteed regularization method for maximum likelihood estimation using gauge symmetry in Kullback-Leibler divergence.

Bio-inspired neural networks use predictive coding for efficient weight updates.

A new predictive coding algorithm improves machine learning performance.

Corrected samplers reduce discretization error in discrete flow models without additional computational cost.

PredNet, a deep predictive coding network developed by Lotter et al., combines a biologically inspired architecture based on the propagation of prediction error with self-supervised representation learning in video. While the architecture has drawn a lot of attention and various extensions of the model exist, there is …

New estimator corrects bias in CKA for sparsely sampled neurons.

Study on topological order on fractal geometries, proving no-go theorem and fault-tolerant gates.

Training-free method improves text-to-image generation quality.

The use of Reinforcement Learning in real-world scenarios is strongly limited by issues of scale. Most RL learning algorithms are unable to deal with problems composed of hundreds or sometimes even dozens of possible actions, and therefore cannot be applied to many real-world problems. We consider the RL problem in the…

New method corrects correlation bias in feature importance.

Classification Ensemble, which uses the weighed polling of outputs, is the art of combining a set of basic classifiers for generating high-performance, robust and more stable results. This study aims to improve the results of identifying the Persian handwritten letters using Error Correcting Output Coding (ECOC) ensemb…

Study neural communication systems with bandwidth-limited channels.