Large pre-trained models have proved to be remarkable zero- and (prompt-based) few-shot learners in unimodal vision and language tasks. We propose MAPL, a simple and parameter-efficient method that reuses frozen pre-trained unimodal models and leverages their strong generalization capabilities in multimodal vision-language (VL) settings. MAPL learns a lightweight mapping between the representation spaces of unimodal models using aligned image-text data, and can generalize to unseen VL tasks from just a few in-context examples. The small number of trainable parameters makes MAPL effective at low-data and in-domain learning. Moreover, MAPL's modularity enables easy extension to other pre-trained models. Extensive experiments on several visual question answering and image captioning benchmarks show that MAPL achieves superior or competitive performance compared to similar methods while training orders of magnitude fewer parameters. MAPL can be trained in just a few hours using modest computational resources and public datasets. We release our code and pre-trained model weights at https://github.com/mair-lab/mapl.

Words are fundamental linguistic units that connect thoughts and things through meaning. However, words do not appear independently in a text sequence. The existence of syntactic rules induces correlations among neighboring words. Using an ordinal pattern approach, we present an analysis of lexical statistical connections for 11 major languages. We find that the diverse manners that languages utilize to express word relations give rise to unique pattern structural distributions. Furthermore, fluctuations of these pattern distributions for a given language can allow us to determine both the historical period when the text was written and its author. Taken together, our results emphasize the relevance of ordinal time series analysis in linguistic typology, historical linguistics and stylometry.

Catastrophic forgetting in neural networks during incremental learning remains a challenging problem. Previous research investigated catastrophic forgetting in fully connected networks, with some earlier work exploring activation functions and learning algorithms. Applications of neural networks have been extended to include similarity learning. Understanding how similarity learning loss functions would be affected by catastrophic forgetting is of significant interest. Our research investigates catastrophic forgetting for four well-known similarity-based loss functions during incremental class learning. The loss functions are Angular, Contrastive, Center, and Triplet loss. Our results show that the catastrophic forgetting rate differs across loss functions on multiple datasets. The Angular loss was least affected, followed by Contrastive, Triplet loss, and Center loss with good mining techniques. We implemented three existing incremental learning techniques, iCaRL, EWC, and EBLL. We further proposed a novel technique using Variational Autoencoders (VAEs) to generate representation as exemplars passed through the network's intermediate layers. Our method outperformed three existing state-of-the-art techniques. We show that one does not require stored images (exemplars) for incremental learning with similarity learning. The generated representations from VAEs help preserve regions of the embedding space used by prior knowledge so that new knowledge does not ``overwrite'' it.

Adversarial training is an effective but time-consuming way to train robust deep neural networks that can withstand strong adversarial attacks. As a response to its inefficiency, we propose Dynamic Efficient Adversarial Training (DEAT), which gradually increases the adversarial iteration during training. We demonstrate that the gradient's magnitude correlates with the curvature of the trained model's loss landscape, allowing it to reflect the effect of adversarial training. Therefore, based on the magnitude of the gradient, we propose a general acceleration strategy, M+ acceleration, which enables an automatic and highly effective method of adjusting the training procedure. M+ acceleration is computationally efficient and easy to implement. It is suited for DEAT and compatible with the majority of existing adversarial training techniques. Extensive experiments have been done on CIFAR-10 and ImageNet datasets with various training environments. The results show that the proposed M+ acceleration significantly improves the training efficiency of existing adversarial training methods while achieving similar robustness performance. This demonstrates that the strategy is highly adaptive and offers a valuable solution for automatic adversarial training.

Abstract--In this paper, we propose an explanation of representation for self-attention network (SAN) based neural sequence encoders, which regards the information captured by the model and the encoding of the model as graph structure and the generation of these graph structures respectively. The proposed explanation applies to existing works on SAN-based models and can explain the relationship among the ability to capture the structural or linguistic information, depth of model, and length of sentence, and can also be extended to other models such as recurrent neural network based models. We also propose a revisited multigraph called Multi-order-Graph (MoG) based on our explanation to model the graph structures in the SAN-based model as subgraphs in MoG and convert the encoding of SAN-based model to the generation of MoG. Based on our explanation, we further introduce a Graph-Transformer by enhancing the ability to capture multiple subgraphs of different orders and focusing on subgraphs of high orders. Experimental results on multiple neural machine translation tasks show that the Graph-Transformer can yield effective performance improvement. These works show that SAN-based models can embed structural which the encoder takes a sentence as input and generates the and linguistic information, and the information embedding ability corresponding contextualized representations for the decoder for is related to the model depth and sentence length. So far, although NLP tasks with various we may get intuitions as follows, (1) different layers in SANbased modeling ways, generally, there are mainly three types of encoder models may deliver different sorts of information, (2) architectures, recurrent neural network (RNN) [1], [2], [3], convolutional increasing the depth of the model can improve the performance neural network (CNN), and self-attention network (SAN) while improvement may be tiny when the model is too deep, from Transformer [4].

Neural networks adapt very well to distributed and continuous representations, but struggle to generalize from small amounts of data. Symbolic systems commonly achieve data efficient generalization by exploiting modularity to benefit from local and discrete features of a representation. These features allow symbolic programs to be improved one module at a time and to experience combinatorial growth in the values they can successfully process. However, it is difficult to design a component that can be used to form symbolic abstractions and which is adequately overparametrized to learn arbitrary high-dimensional transformations. I present Graph-based Symbolically Synthesized Neural Networks (G-SSNNs), a class of neural modules that operate on representations modified with synthesized symbolic programs to include a fixed set of local and discrete features. I demonstrate that the choice of injected features within a G-SSNN module modulates the data efficiency and generalization of baseline neural models, creating predictable patterns of both heightened and curtailed generalization. By training G-SSNNs, we also derive information about desirable semantics of symbolic programs without manual engineering. This information is compact and amenable to abstraction, but can also be flexibly recontextualized for other high-dimensional settings. In future work, I will investigate data efficient generalization and the transferability of learned symbolic representations in more complex G-SSNN designs based on more complex classes of symbolic programs. Experimental code and data are available at https://github.com/shlomenu/symbolically_synthesized_networks .

Infectious diseases remain among the top contributors to human illness and death worldwide, among which many diseases produce epidemic waves of infection. The unavailability of specific drugs and ready-to-use vaccines to prevent most of these epidemics makes the situation worse. These force public health officials and policymakers to rely on early warning systems generated by reliable and accurate forecasts of epidemics. Accurate forecasts of epidemics can assist stakeholders in tailoring countermeasures, such as vaccination campaigns, staff scheduling, and resource allocation, to the situation at hand, which could translate to reductions in the impact of a disease. Unfortunately, most of these past epidemics exhibit nonlinear and non-stationary characteristics due to their spreading fluctuations based on seasonal-dependent variability and the nature of these epidemics. We analyse a wide variety of epidemic time series datasets using a maximal overlap discrete wavelet transform (MODWT) based autoregressive neural network and call it EWNet model. MODWT techniques effectively characterize non-stationary behavior and seasonal dependencies in the epidemic time series and improve the nonlinear forecasting scheme of the autoregressive neural network in the proposed ensemble wavelet network framework. From a nonlinear time series viewpoint, we explore the asymptotic stationarity of the proposed EWNet model to show the asymptotic behavior of the associated Markov Chain. We also theoretically investigate the effect of learning stability and the choice of hidden neurons in the proposal. From a practical perspective, we compare our proposed EWNet framework with several statistical, machine learning, and deep learning models. Experimental results show that the proposed EWNet is highly competitive compared to the state-of-the-art epidemic forecasting methods.

The discussion of Artificial Intelligence (AI) has become so prevalent that every sector is now informed of its existence. Over the years, technology has been a major driving force in growing and developing human work states and engagements. With various examples of newly developed AI, the adoption of this digital revolution has become so paramount to everyone. However, an important question I have amid all these is, "how will AI help developing Third World countries?" It is important to first examine what third-world countries are before delving into the ways in which AI can help them better.

New AI systems such as ChatGPT, the overhauled Microsoft Bing search engine, and the reportedly soon-to-arrive GPT-4 have utterly captured the public imagination. ChatGPT is the fastest-growing online application, ever, and it's no wonder why. Type in some text, and instead of getting back web links, you get well-formed, conversational responses on whatever topic you selected--an undeniably seductive vision. But the public, and the tech giants, aren't the only ones who have become enthralled with the Big Data–driven technology known as the large language model. Bad actors have taken note of the technology as well. At the extreme end, there's Andrew Torba, the CEO of the far-right social network Gab, who said recently that his company is actively developing AI tools to "uphold a Christian worldview" and fight "the censorship tools of the Regime."

From South Juba to Entebbe, from Marrakesh to Accra, on the cusp of technology in Africa, the need for responsible AI development and ethical data practices has never been more pressing. As technology continues to advance and shape the global economy, Africa is taking steps toward positioning itself as a leader in Artificial Intelligence (AI). Investments and innovations in AI are on the rise across the continent, with a growing number of countries beginning to develop policies and strategies to harness the power of this transformative technology. Although only a few countries have officially adopted AI strategies and policies, many more are actively working towards defining their AI policies. As philosopher and economist Amartya Sen noted, 'Development requires the removal of major sources of unfreedom that leave people with little choice and little opportunity of exercising their reasoned agency.'