In this work, we demonstrate the offline FPGA realization of both recurrent and feedforward neural network (NN)-based equalizers for nonlinearity compensation in coherent optical transmission systems. First, we present a realization pipeline showing the conversion of the models from Python libraries to the FPGA chip synthesis and implementation. Then, we review the main alternatives for the hardware implementation of nonlinear activation functions. The main results are divided into three parts: a performance comparison, an analysis of how activation functions are implemented, and a report on the complexity of the hardware. The performance in Q-factor is presented for the cases of bidirectional long-short-term memory coupled with convolutional NN (biLSTM + CNN) equalizer, CNN equalizer, and standard 1-StpS digital back-propagation (DBP) for the simulation and experiment propagation of a single channel dual-polarization (SC-DP) 16QAM at 34 GBd along 17x70km of LEAF. The biLSTM+CNN equalizer provides a similar result to DBP and a 1.7 dB Q-factor gain compared with the chromatic dispersion compensation baseline in the experimental dataset. After that, we assess the Q-factor and the impact of hardware utilization when approximating the activation functions of NN using Taylor series, piecewise linear, and look-up table (LUT) approximations. We also show how to mitigate the approximation errors with extra training and provide some insights into possible gradient problems in the LUT approximation. Finally, to evaluate the complexity of hardware implementation to achieve 400G throughput, fixed-point NN-based equalizers with approximated activation functions are developed and implemented in an FPGA.

To circumvent the non-parallelizability of recurrent neural network-based equalizers, we propose knowledge distillation to recast the RNN into a parallelizable feedforward structure. The latter shows 38\% latency decrease, while impacting the Q-factor by only 0.5dB.

在本文中，提出了一种新的方法，该方法允许基于神经网络（NN）均衡器的低复杂性发展，以缓解高速相干光学传输系统中的损伤。在这项工作中，我们提供了已应用于馈电和经常性NN设计的各种深层模型压缩方法的全面描述和比较。此外，我们评估了这些策略对每个NN均衡器的性能的影响。考虑量化，重量聚类，修剪和其他用于模型压缩的尖端策略。在这项工作中，我们提出并评估贝叶斯优化辅助压缩，其中选择了压缩的超参数以同时降低复杂性并提高性能。总之，通过使用模拟和实验数据来评估每种压缩方法的复杂性及其性能之间的权衡，以完成分析。通过利用最佳压缩方法，我们表明可以设计基于NN的均衡器，该均衡器比传统的数字背部传播（DBP）均衡器具有更好的性能，并且只有一个步骤。这是通过减少使用加权聚类和修剪算法后在NN均衡器中使用的乘数数量来完成的。此外，我们证明了基于NN的均衡器也可以实现卓越的性能，同时仍然保持与完整的电子色色散补偿块相同的复杂性。我们通过强调开放问题和现有挑战以及未来的研究方向来结束分析。

FPGA中首次实施了针对非线性补偿的经常性和前馈神经网络均衡器，其复杂度与分散均衡器的复杂度相当。我们证明，基于NN的均衡器可以胜过1个速度的DBP。

Recently, there has been an interest in improving the resources available in Intrusion Detection System (IDS) techniques. In this sense, several studies related to cybersecurity show that the environment invasions and information kidnapping are increasingly recurrent and complex. The criticality of the business involving operations in an environment using computing resources does not allow the vulnerability of the information. Cybersecurity has taken on a dimension within the universe of indispensable technology in corporations, and the prevention of risks of invasions into the environment is dealt with daily by Security teams. Thus, the main objective of the study was to investigate the Ensemble Learning technique using the Stacking method, supported by the Support Vector Machine (SVM) and k-Nearest Neighbour (kNN) algorithms aiming at an optimization of the results for DDoS attack detection. For this, the Intrusion Detection System concept was used with the application of the Data Mining and Machine Learning Orange tool to obtain better results

Candidate axiom scoring is the task of assessing the acceptability of a candidate axiom against the evidence provided by known facts or data. The ability to score candidate axioms reliably is required for automated schema or ontology induction, but it can also be valuable for ontology and/or knowledge graph validation. Accurate axiom scoring heuristics are often computationally expensive, which is an issue if you wish to use them in iterative search techniques like level-wise generate-and-test or evolutionary algorithms, which require scoring a large number of candidate axioms. We address the problem of developing a predictive model as a substitute for reasoning that predicts the possibility score of candidate class axioms and is quick enough to be employed in such situations. We use a semantic similarity measure taken from an ontology's subsumption structure for this purpose. We show that the approach provided in this work can accurately learn the possibility scores of candidate OWL class axioms and that it can do so for a variety of OWL class axioms.

Automatic Text Summarization (ATS) is becoming relevant with the growth of textual data; however, with the popularization of public large-scale datasets, some recent machine learning approaches have focused on dense models and architectures that, despite producing notable results, usually turn out in models difficult to interpret. Given the challenge behind interpretable learning-based text summarization and the importance it may have for evolving the current state of the ATS field, this work studies the application of two modern Generalized Additive Models with interactions, namely Explainable Boosting Machine and GAMI-Net, to the extractive summarization problem based on linguistic features and binary classification.

We describe a Physics-Informed Neural Network (PINN) that simulates the flow induced by the astronomical tide in a synthetic port channel, with dimensions based on the Santos - S\~ao Vicente - Bertioga Estuarine System. PINN models aim to combine the knowledge of physical systems and data-driven machine learning models. This is done by training a neural network to minimize the residuals of the governing equations in sample points. In this work, our flow is governed by the Navier-Stokes equations with some approximations. There are two main novelties in this paper. First, we design our model to assume that the flow is periodic in time, which is not feasible in conventional simulation methods. Second, we evaluate the benefit of resampling the function evaluation points during training, which has a near zero computational cost and has been verified to improve the final model, especially for small batch sizes. Finally, we discuss some limitations of the approximations used in the Navier-Stokes equations regarding the modeling of turbulence and how it interacts with PINNs.

As language models (LMs) scale, they develop many novel behaviors, good and bad, exacerbating the need to evaluate how they behave. Prior work creates evaluations with crowdwork (which is time-consuming and expensive) or existing data sources (which are not always available). Here, we automatically generate evaluations with LMs. We explore approaches with varying amounts of human effort, from instructing LMs to write yes/no questions to making complex Winogender schemas with multiple stages of LM-based generation and filtering. Crowdworkers rate the examples as highly relevant and agree with 90-100% of labels, sometimes more so than corresponding human-written datasets. We generate 154 datasets and discover new cases of inverse scaling where LMs get worse with size. Larger LMs repeat back a dialog user's preferred answer ("sycophancy") and express greater desire to pursue concerning goals like resource acquisition and goal preservation. We also find some of the first examples of inverse scaling in RL from Human Feedback (RLHF), where more RLHF makes LMs worse. For example, RLHF makes LMs express stronger political views (on gun rights and immigration) and a greater desire to avoid shut down. Overall, LM-written evaluations are high-quality and let us quickly discover many novel LM behaviors.

As AI systems become more capable, we would like to enlist their help to supervise other AIs. We experiment with methods for training a harmless AI assistant through self-improvement, without any human labels identifying harmful outputs. The only human oversight is provided through a list of rules or principles, and so we refer to the method as 'Constitutional AI'. The process involves both a supervised learning and a reinforcement learning phase. In the supervised phase we sample from an initial model, then generate self-critiques and revisions, and then finetune the original model on revised responses. In the RL phase, we sample from the finetuned model, use a model to evaluate which of the two samples is better, and then train a preference model from this dataset of AI preferences. We then train with RL using the preference model as the reward signal, i.e. we use 'RL from AI Feedback' (RLAIF). As a result we are able to train a harmless but non-evasive AI assistant that engages with harmful queries by explaining its objections to them. Both the SL and RL methods can leverage chain-of-thought style reasoning to improve the human-judged performance and transparency of AI decision making. These methods make it possible to control AI behavior more precisely and with far fewer human labels.