We propose spectrum-sliced reservoir computer-based (RC) multi-symbol equalization for 32-GBd PAM4 transmission. RC with 17 symbols at the output achieves an order of magnitude reduction in multiplications/symbol versus single output case while maintaining simple training.

We demonstrate transfer learning-assisted neural network models for optical matrix multipliers with scarce measurement data. Our approach uses <10\% of experimental data needed for best performance and outperforms analytical models for a Mach-Zehnder interferometer mesh.

我们通过实验验证一个实时机器学习框架，能够控制拉曼放大器的泵功率值以在二维（2D）中塑造信号功率演变：频率和光纤距离。在我们的设置中，优化了四个一阶反向传输泵的功率值，以实现所需的2D功率配置文件。泵功率优化框架包括一个卷积神经网络（CNN），然后是差分进化（DE）技术，在线应用于放大器设置，以自动实现目标2D功率配置文件。可实现的2D配置文件的结果表明，该框架能够确保获得的最大绝对误差（MAE）（<0.5 dB）与获得的目标2D配置文件之间。此外，该框架在多目标设计方案中进行了测试，该方案的目标是在跨度结束时达到固定增益水平的2D配置文件，共同在整个光纤长度上进行最小的光谱游览。在这种情况下，实验结果断言，对于目标扁平增益水平的2D轮廓，当设置在泵功率值中不受物理限制时，DE获得的最大增益偏差小于1 dB。模拟结果还证明，有足够的泵功率可用，可以实现更高的目标增益水平的更好的增益偏差（小于0.6 dB）。

研究了拉曼放大器优化的问题。使用机器学习（ML）获得了拉曼增益系数的可区分插值函数，该函数允许对前向传播拉曼泵的梯度下降优化。然后，针对任意数据通道负载和跨度长度优化了向前泵送配置中任意数量的泵的频率和功率。向前倾斜的拉曼放大器的实验训练的ML模型将正向传播模型结合在一起，以共同优化前向放大器泵的频率和功率以及向后放大器泵的功率。对于250 km的未重新曝光，展示了关节向前和向后放大器的优化。超过4 THz的增益平坦度为$ <$ 1〜 dB。使用数值模拟器验证了优化的放大器。

在随机子集总和问题中，给定$ n $ i.i.d.随机变量$ x_1，...，x_n $，我们希望将[-1,1] $ in [-1,1] $的任何点$ z \作为合适子集的总和$ x_ {i_1（z）}，...，x_ {i_s（z）} $的$，最多$ \ varepsilon $。尽管有简单的陈述，但这个问题还是理论计算机科学和统计力学的基本兴趣。最近，它因其在人工神经网络理论中的影响而引起了人们的重新关注。该问题的一个明显的多维概括是考虑$ n $ i.i.d. \ $ d $ - 二维随机向量，目的是近似于[-1,1]^d $的每个点$ \ Mathbf {z} \。令人惊讶的是，在Lueker的1998年证明，在一维设置中，$ n = o（\ log \ frac 1 \ varepsilon）$ samples $ samples $ samples具有很高可能性的近似属性，在实现上述概括方面几乎没有进展。在这项工作中，我们证明，在$ d $ dimensions中，$ n = o（d^3 \ log \ frac 1 \ varepsilon \ cdot（\ log \ frac 1 \ frac 1 \ varepsilon + log d d））$ samples $ sample近似属性具有很高的概率。作为强调该结果潜在兴趣的应用程序，我们证明了最近提出的神经网络模型表现出\ emph {通用}：具有很高的概率，该模型可以在参数数量中近似多项式开销中的任何神经网络。

Continual Learning (CL) is a field dedicated to devise algorithms able to achieve lifelong learning. Overcoming the knowledge disruption of previously acquired concepts, a drawback affecting deep learning models and that goes by the name of catastrophic forgetting, is a hard challenge. Currently, deep learning methods can attain impressive results when the data modeled does not undergo a considerable distributional shift in subsequent learning sessions, but whenever we expose such systems to this incremental setting, performance drop very quickly. Overcoming this limitation is fundamental as it would allow us to build truly intelligent systems showing stability and plasticity. Secondly, it would allow us to overcome the onerous limitation of retraining these architectures from scratch with the new updated data. In this thesis, we tackle the problem from multiple directions. In a first study, we show that in rehearsal-based techniques (systems that use memory buffer), the quantity of data stored in the rehearsal buffer is a more important factor over the quality of the data. Secondly, we propose one of the early works of incremental learning on ViTs architectures, comparing functional, weight and attention regularization approaches and propose effective novel a novel asymmetric loss. At the end we conclude with a study on pretraining and how it affects the performance in Continual Learning, raising some questions about the effective progression of the field. We then conclude with some future directions and closing remarks.

Computational units in artificial neural networks follow a simplified model of biological neurons. In the biological model, the output signal of a neuron runs down the axon, splits following the many branches at its end, and passes identically to all the downward neurons of the network. Each of the downward neurons will use their copy of this signal as one of many inputs dendrites, integrate them all and fire an output, if above some threshold. In the artificial neural network, this translates to the fact that the nonlinear filtering of the signal is performed in the upward neuron, meaning that in practice the same activation is shared between all the downward neurons that use that signal as their input. Dendrites thus play a passive role. We propose a slightly more complex model for the biological neuron, where dendrites play an active role: the activation in the output of the upward neuron becomes optional, and instead the signals going through each dendrite undergo independent nonlinear filterings, before the linear combination. We implement this new model into a ReLU computational unit and discuss its biological plausibility. We compare this new computational unit with the standard one and describe it from a geometrical point of view. We provide a Keras implementation of this unit into fully connected and convolutional layers and estimate their FLOPs and weights change. We then use these layers in ResNet architectures on CIFAR-10, CIFAR-100, Imagenette, and Imagewoof, obtaining performance improvements over standard ResNets up to 1.73%. Finally, we prove a universal representation theorem for continuous functions on compact sets and show that this new unit has more representational power than its standard counterpart.

Detecting anomalous data within time series is a very relevant task in pattern recognition and machine learning, with many possible applications that range from disease prevention in medicine, e.g., detecting early alterations of the health status before it can clearly be defined as "illness" up to monitoring industrial plants. Regarding this latter application, detecting anomalies in an industrial plant's status firstly prevents serious damages that would require a long interruption of the production process. Secondly, it permits optimal scheduling of maintenance interventions by limiting them to urgent situations. At the same time, they typically follow a fixed prudential schedule according to which components are substituted well before the end of their expected lifetime. This paper describes a case study regarding the monitoring of the status of Laser-guided Vehicles (LGVs) batteries, on which we worked as our contribution to project SUPER (Supercomputing Unified Platform, Emilia Romagna) aimed at establishing and demonstrating a regional High-Performance Computing platform that is going to represent the main Italian supercomputing environment for both computing power and data volume.

Recent object detection models for infrared (IR) imagery are based upon deep neural networks (DNNs) and require large amounts of labeled training imagery. However, publicly-available datasets that can be used for such training are limited in their size and diversity. To address this problem, we explore cross-modal style transfer (CMST) to leverage large and diverse color imagery datasets so that they can be used to train DNN-based IR image based object detectors. We evaluate six contemporary stylization methods on four publicly-available IR datasets - the first comparison of its kind - and find that CMST is highly effective for DNN-based detectors. Surprisingly, we find that existing data-driven methods are outperformed by a simple grayscale stylization (an average of the color channels). Our analysis reveals that existing data-driven methods are either too simplistic or introduce significant artifacts into the imagery. To overcome these limitations, we propose meta-learning style transfer (MLST), which learns a stylization by composing and tuning well-behaved analytic functions. We find that MLST leads to more complex stylizations without introducing significant image artifacts and achieves the best overall detector performance on our benchmark datasets.

Objective: Accurate visual classification of bladder tissue during Trans-Urethral Resection of Bladder Tumor (TURBT) procedures is essential to improve early cancer diagnosis and treatment. During TURBT interventions, White Light Imaging (WLI) and Narrow Band Imaging (NBI) techniques are used for lesion detection. Each imaging technique provides diverse visual information that allows clinicians to identify and classify cancerous lesions. Computer vision methods that use both imaging techniques could improve endoscopic diagnosis. We address the challenge of tissue classification when annotations are available only in one domain, in our case WLI, and the endoscopic images correspond to an unpaired dataset, i.e. there is no exact equivalent for every image in both NBI and WLI domains. Method: We propose a semi-surprised Generative Adversarial Network (GAN)-based method composed of three main components: a teacher network trained on the labeled WLI data; a cycle-consistency GAN to perform unpaired image-to-image translation, and a multi-input student network. To ensure the quality of the synthetic images generated by the proposed GAN we perform a detailed quantitative, and qualitative analysis with the help of specialists. Conclusion: The overall average classification accuracy, precision, and recall obtained with the proposed method for tissue classification are 0.90, 0.88, and 0.89 respectively, while the same metrics obtained in the unlabeled domain (NBI) are 0.92, 0.64, and 0.94 respectively. The quality of the generated images is reliable enough to deceive specialists. Significance: This study shows the potential of using semi-supervised GAN-based classification to improve bladder tissue classification when annotations are limited in multi-domain data.