1,724,622 research outputs found
Decima relazione al Parlamento sullo stato di attuazione della legge 12 marzo 999, n. 68 “Norme per il diritto al lavoro dei disabili” anno 2019
No full textLa decima edizione della relazione illustra i risultati dell’attività svolta nel corso del 2019 dai servizi territorialmente competenti in Italia, nonché i principali andamenti del sistema del collocamento mirato riferiti alla medesima annualità. In continuità con quanto rilevato nella precedente Relazione sul triennio 2016-2018, anche il 2019 si connota per una crescita occupazionale significativa, che ha interessato l’intero territorio nazionale, accompagnata da analoghi incrementi nelle iscrizioni agli elenchi del collocamento obbligatorio e nella quota di riserva nazionale espressa da un numero maggiore di datori pubblici e privati sottoposti ad obblighi di legge. La X Relazione prende in esame un’unica annualità per ripristinare la ciclicità biennale prevista dal legislatore, modificata eccezionalmente nella precedente edizione con la copertura del triennio 2016-2018.la decima edizione della relazione illustra i risultati dell’attività svolta nel corso del 2019 dai servizi territorialmente competenti in italia, nonché i principali andamenti del sistema del collocamento mirato riferiti alla medesima annualità. in continuità con quanto rilevato nella precedente relazione sul triennio 2016-2018, anche il 2019 si connota per una crescita occupazionale significativa, che ha interessato l’intero territorio nazionale, accompagnata da analoghi incrementi nelle iscrizioni agli elenchi del collocamento obbligatorio e nella quota di riserva nazionale espressa da un numero maggiore di datori pubblici e privati sottoposti ad obblighi di legge. la x relazione prende in esame un’unica annualità per ripristinare la ciclicità biennale prevista dal legislatore, modificata eccezionalmente nella precedente edizione con la copertura del triennio 2016-2018. decima relazione al parlamento sullo stato di attuazione della legge 12 marzo 999, n. 68 “norme per il diritto al lavoro dei disabili” anno 201
Undicesima relazione al Parlamento sullo stato di attuazione della legge 12 marzo 1999, n. 68 “Norme per il diritto al lavoro dei disabili”, Anni 2020-2021
Full text linkLa Relazione raccoglie informazioni, dati e analisi sullo stato di attuazione della legge 68/99 nel biennio 2020-2021 e risponde all'obbligo di riferire al Parlamento ai sensi dell'articolo 21 legge 68/99. Nel dettaglio, illustra e analizza l’applicazione del collocamento mirato delle persone con disabilità e gli esiti delle politiche poste in essere, anche in ottica di genere. Rispetto alle precedenti Relazioni, la presente edizione introduce nuove modalità di analisi statistica dei dati, per rappresentare le dimensioni e gli andamenti delle principali variabili del collocamento mirato nel corso di oltre un decennio, su aggregati nazionali e per aree geografiche.la relazione raccoglie informazioni, dati e analisi sullo stato di attuazione della legge 68/99 nel biennio 2020-2021 e risponde all'obbligo di riferire al parlamento ai sensi dell'articolo 21 legge 68/99. nel dettaglio, illustra e analizza l’applicazione del collocamento mirato delle persone con disabilità e gli esiti delle politiche poste in essere, anche in ottica di genere. rispetto alle precedenti relazioni, la presente edizione introduce nuove modalità di analisi statistica dei dati, per rappresentare le dimensioni e gli andamenti delle principali variabili del collocamento mirato nel corso di oltre un decennio, su aggregati nazionali e per aree geografiche. undicesima relazione al parlamento sullo stato di attuazione della legge 12 marzo 1999, n. 68 “norme per il diritto al lavoro dei disabili”, anni 2020-202
S.-Pombe-MLPs
No full textThis repository contains all the code to produce the findings in https://www.biorxiv.org/content/10.1101/2023.12.15.571870v2 as well as in my Master's thesis.</p
Scaling MLPs: A Tale of Inductive Bias
Full text linkIn this work we revisit the most fundamental building block in deep learning,
the multi-layer perceptron (MLP), and study the limits of its performance on
vision tasks. Empirical insights into MLPs are important for multiple reasons.
(1) Given the recent narrative "less inductive bias is better", popularized due
to transformers eclipsing convolutional models, it is natural to explore the
limits of this hypothesis. To that end, MLPs offer an ideal test bed, as they
lack any vision-specific inductive bias. (2) MLPs have almost exclusively been
the main protagonist in the deep learning theory literature due to their
mathematical simplicity, serving as a proxy to explain empirical phenomena
observed for more complex architectures. Surprisingly, experimental datapoints
for MLPs are very difficult to find in the literature, especially when coupled
with large pre-training protocols. This discrepancy between practice and theory
is worrying: Do MLPs reflect the empirical advances exhibited by practical
models? Or do theorists need to rethink the role of MLPs as a proxy? We provide
insights into both these aspects. We show that the performance of MLPs
drastically improves with scale (95% on CIFAR10, 82% on CIFAR100, 58% on
ImageNet ReaL), highlighting that lack of inductive bias can indeed be
compensated. We observe that MLPs mimic the behaviour of their modern
counterparts faithfully, with some components in the learning setting however
exhibiting stronger or unexpected behaviours. Due to their inherent
computational efficiency, large pre-training experiments become more accessible
for academic researchers. All of our experiments were run on a single GPU
SimMLP: Training MLPs on Graphs without Supervision
No full textGraph Neural Networks (GNNs) have demonstrated their effectiveness in various graph learning tasks, yet their reliance on neighborhood aggregation during inference poses challenges for deployment in latency-sensitive applications, such as real-time financial fraud detection. To address this limitation, recent studies have proposed distilling knowledge from teacher GNNs into student Multi-Layer Perceptrons (MLPs) trained on node content, aiming to accelerate inference. However, these approaches often inadequately explore structural information when inferring unseen nodes. To this end, we introduce SimMLP, a Self-supervised framework for learning MLPs on graphs, designed to fully integrate rich structural information into MLPs. Notably, SimMLP is the first MLP-learning method that can achieve equivalence to GNNs in the optimal case. The key idea is to employ self-supervised learning to align the representations encoded by graph context-aware GNNs and neighborhood dependency-free MLPs, thereby fully integrating the structural information into MLPs. We provide a comprehensive theoretical analysis, demonstrating the equivalence between SimMLP and GNNs based on mutual information and inductive bias, highlighting SimMLP\u27s advanced structural learning capabilities. Additionally, we conduct extensive experiments on 20 benchmark datasets, covering node classification, link prediction, and graph classification, to showcase SimMLP\u27s superiority over state-of-the-art baselines, particularly in scenarios involving unseen nodes (e.g., inductive and cold-start node classification) where structural insights are crucial. Our codes are available at: https://github.com/Zehong-Wang/SimMLP.New Version: arXiv:2412.0386
Learning Nonlinear Functions with MLPs and SRNs
Full text linkIn this paper, nonlinear functions generated by randomly initialized multilayer perceptrons (MLPs) and simultaneous recurrent neural networks (SRNs) are learned by MLPs and SRNs. Training SRNs is a challenging task and a new learning algorithm - DEPSO is introduced. DEPSO is a standard particle swarm optimization (PSO) algorithm with the addition of a differential evolution step to aid in swarm convergence. The results from DEPSO are compared with the standard backpropagation (BP) and PSO algorithms. It is further verified that functions generated by SRNs are harder to learn than those generated by MLPs but DEPSO provides better learning capabilities for the functions generated by MLPs and SRNs as compared to BP and PSO. These three algorithms are also trained on several benchmark functions to confirm results
Training MLPs on Graphs without Supervision
No full textGraph Neural Networks (GNNs) have demonstrated their effectiveness in various graph learning tasks, yet their reliance on neighborhood aggregation during inference poses challenges for deployment in latency-sensitive applications, such as real-time financial fraud detection. To address this limitation, recent studies have proposed distilling knowledge from teacher GNNs into student Multi-Layer Perceptrons (MLPs) trained on node content, aiming to accelerate inference. However, these approaches often inadequately explore structural information when inferring unseen nodes. To this end, we introduce SimMLP, a Self-supervised framework for learning MLPs on graphs, designed to fully integrate rich structural information into MLPs. Notably, SimMLP is the first MLP-learning method that can achieve equivalence to GNNs in the optimal case. The key idea is to employ self-supervised learning to align the representations encoded by graph context-aware GNNs and neighborhood dependency-free MLPs, thereby fully integrating the structural information into MLPs. We provide a comprehensive theoretical analysis, demonstrating the equivalence between SimMLP and GNNs based on mutual information and inductive bias, highlighting SimMLP\u27s advanced structural learning capabilities. Additionally, we conduct extensive experiments on 20 benchmark datasets, covering node classification, link prediction, and graph classification, to showcase SimMLP\u27s superiority over state-of-the-art baselines, particularly in scenarios involving unseen nodes (e.g., inductive and cold-start node classification) where structural insights are crucial. Our codes are available at: https://github.com/Zehong-Wang/SimMLP.Accepted by WSDM 2
Modern Languages in the Primary School (MLPS): Some Key Messages
No full textPaper focusing on the Modern Languages in the Primary School (MLPS) project. Teachers have reached a good level of linguistic competence and MLPS teachers have a good understanding of pedagogy
Trap of Feature Diversity in the Learning of MLPs
Full text linkIn this paper, we focus on a typical two-phase phenomenon in the learning of
multi-layer perceptrons (MLPs), and we aim to explain the reason for the
decrease of feature diversity in the first phase. Specifically, people find
that, in the training of MLPs, the training loss does not decrease
significantly until the second phase. To this end, we further explore the
reason why the diversity of features over different samples keeps decreasing in
the first phase, which hurts the optimization of MLPs. We explain such a
phenomenon in terms of the learning dynamics of MLPs. Furthermore, we
theoretically explain why four typical operations can alleviate the decrease of
the feature diversity
- …
