Catastrophic forgetting is a significant challenge in the field of machine learning, particularly in neural networks. When a neural network learns to perform well on a new task, it often forgets its previously acquired knowledge or experiences. This phenomenon occurs because the network adjusts its weights and connections to minimize the loss on the new task, which can inadvertently overwrite or disrupt the representations that were crucial for the previous tasks. As a result, the the performance of the network on earlier tasks deteriorates, limiting its ability to learn and adapt to a sequence of tasks. In this paper, we propose a novel method for preventing catastrophic forgetting in machine learning applications, specifically focusing on neural networks. Our approach aims to preserve the knowledge of the network across multiple tasks while still allowing it to learn new information effectively. We demonstrate the effectiveness of our method by conducting experiments on various benchmark datasets, including Split MNIST, Split CIFAR10, Split Fashion MNIST, and Split CIFAR100. These datasets are created by dividing the original datasets into separate, non overlapping tasks, simulating a continual learning scenario where the model needs to learn multiple tasks sequentially without forgetting the previous ones. Our proposed method tackles the catastrophic forgetting problem by incorporating negotiated representations into the learning process, which allows the model to maintain a balance between retaining past experiences and adapting to new tasks. By evaluating our method on these challenging datasets, we aim to showcase its potential for addressing catastrophic forgetting and improving the performance of neural networks in continual learning settings.

People with visual impairments have difficulty accessing touchscreen-enabled personal computing devices like mobile phones and laptops. The image-to-speech (ITS) systems can assist them in mitigating this problem, but their huge model size makes it extremely hard to be deployed on low-resourced embedded devices. In this paper, we aim to overcome this challenge by developing an efficient endto-end neural architecture for generating audio from tiny segments of display content on low-resource devices. We introduced a vision transformers-based image encoder and utilized knowledge distillation to compress the model from 6.1 million to 2.46 million parameters. Human and automatic evaluation results show that our approach leads to a very minimal drop in performance and can speed up the inference time by 22%.

Can a physicist make only finite errors in the endless pursuit of the law of nature? This millennium-old question of inductive inference is a fundamental, yet mysterious problem in philosophy, lacking rigorous justifications. While classic online learning theory and inductive inference share a similar sequential decision-making spirit, the former's reliance on an adaptive adversary and worst-case error bounds limits its applicability to the latter. In this work, we introduce the concept of non-uniform online learning, which we argue aligns more closely with the principles of inductive reasoning. This setting assumes a predetermined ground-truth hypothesis and considers non-uniform, hypothesis-wise error bounds. In the realizable setting, we provide a complete characterization of learnability with finite error: a hypothesis class is non-uniform learnable if and only if it's a countable union of Littlestone classes, no matter the observations are adaptively chosen or iid sampled. Additionally, we propose a necessary condition for the weaker criterion of consistency which we conjecture to be tight. To further promote our theory, we extend our result to the more realistic agnostic setting, showing that any countable union of Littlestone classes can be learnt with regret $\tilde{O}(\sqrt{T})$. We hope this work could offer a new perspective of interpreting the power of induction from an online learning viewpoint.

Existing long video retrieval systems are trained and tested in the paragraph-to-video retrieval regime, where every long video is described by a single long paragraph. This neglects the richness and variety of possible valid descriptions of a video, which could be described in moment-by-moment detail, or in a single phrase summary, or anything in between. To provide a more thorough evaluation of the capabilities of long video retrieval systems, we propose a pipeline that leverages state-of-the-art large language models to carefully generate a diverse set of synthetic captions for long videos. We validate this pipeline's fidelity via rigorous human inspection. We then benchmark a representative set of video language models on these synthetic captions using a few long video datasets, showing that they struggle with the transformed data, especially the shortest captions. We also propose a lightweight fine-tuning method, where we use a contrastive loss to learn a hierarchical embedding loss based on the differing levels of information among the various captions. Our method improves performance both on the downstream paragraph-to-video retrieval task (+1.1% R@1 on ActivityNet), as well as for the various long video retrieval metrics we compute using our synthetic data (+3.6% R@1 for short descriptions on ActivityNet). For data access and other details, please refer to our project website at https://mgwillia.github.io/10k-words.

Unsupervised representation learning aims at finding methods that learn representations from data without annotation-based signals. Abstaining from annotations not only leads to economic benefits but may - and to some extent already does - result in advantages regarding the representation's structure, robustness, and generalizability to different tasks. In the long run, unsupervised methods are expected to surpass their supervised counterparts due to the reduction of human intervention and the inherently more general setup that does not bias the optimization towards an objective originating from specific annotation-based signals. While major advantages of unsupervised representation learning have been recently observed in natural language processing, supervised methods still dominate in vision domains for most tasks. In this dissertation, we contribute to the field of unsupervised (visual) representation learning from three perspectives: (i) Learning representations: We design unsupervised, backpropagation-free Convolutional Self-Organizing Neural Networks (CSNNs) that utilize self-organization-and Hebbian-based learning rules to learn convolutional kernels and masks to achieve deeper backpropagation-free models. Thereby, we observe that backpropagation-based and -free methods can suffer from an objective function mismatch between the unsupervised pretext task and the target task. This mismatch can lead to performance decreases for the target task.

Rhetoric, both spoken and written, involves not only content but also style. One common stylistic tool is $\textit{parallelism}$: the juxtaposition of phrases which have the same sequence of linguistic ($\textit{e.g.}$, phonological, syntactic, semantic) features. Despite the ubiquity of parallelism, the field of natural language processing has seldom investigated it, missing a chance to better understand the nature of the structure, meaning, and intent that humans convey. To address this, we introduce the task of $\textit{rhetorical parallelism detection}$. We construct a formal definition of it; we provide one new Latin dataset and one adapted Chinese dataset for it; we establish a family of metrics to evaluate performance on it; and, lastly, we create baseline systems and novel sequence labeling schemes to capture it. On our strictest metric, we attain $F_{1}$ scores of $0.40$ and $0.43$ on our Latin and Chinese datasets, respectively.

In this survey, we offer an extensive overview of the Online Influence Maximization (IM) problem by covering both theoretical aspects and practical applications. For the integrity of the article and because the online algorithm takes an offline oracle as a subroutine, we first make a clear definition of the Offline IM problem and summarize those commonly used Offline IM algorithms, which include traditional approximation or heuristic algorithms and ML-based algorithms. Then, we give a standard definition of the Online IM problem and a basic Combinatorial Multi-Armed Bandit (CMAB) framework, CMAB-T. Here, we summarize three types of feedback in the CMAB model and discuss in detail how to study the Online IM problem based on the CMAB-T model. This paves the way for solving the Online IM problem by using online learning methods. Furthermore, we have covered almost all Online IM algorithms up to now, focusing on characteristics and theoretical guarantees of online algorithms for different feedback types. Here, we elaborately explain their working principle and how to obtain regret bounds. Besides, we also collect plenty of innovative ideas about problem definition and algorithm designs and pioneering works for variants of the Online IM problem and their corresponding algorithms. Finally, we encapsulate current challenges and outline prospective research directions from four distinct perspectives.

Weight initialization plays an important role in neural network training. Widely used initialization methods are proposed and evaluated for networks that are trained from scratch. However, the growing number of pretrained models now offers new opportunities for tackling this classical problem of weight initialization. In this work, we introduce weight selection, a method for initializing smaller models by selecting a subset of weights from a pretrained larger model. This enables the transfer of knowledge from pretrained weights to smaller models. Our experiments demonstrate that weight selection can significantly enhance the performance of small models and reduce their training time. Notably, it can also be used together with knowledge distillation. Weight selection offers a new approach to leverage the power of pretrained models in resource-constrained settings, and we hope it can be a useful tool for training small models in the large-model era. The initialization of neural network weights is crucial for their optimization. Proper initialization aids in model convergence and prevents issues like gradient vanishing. Two prominent initialization techniques, Xavier initialization (Glorot & Bengio, 2010) and Kaiming initialization (He et al., 2015), have played substantial roles in neural network training.

Several scientific communities are currently facing a replication crisis, wherein it has proven difficult or impossible for researchers to independently verify the results of previously published studies. Failures to replicate large swaths of experimental work (Camerer et al., 2018; Nosek et al., 2015; Begley and Ellis, 2012; Baker, 2016) have come in fields like psychology or medicine, that focus on what Hofman et al. (2021) call explanatory modeling, where the goal is to identify and estimate causal effects (e.g., is there an effect of X on Y, and if so, how large is it?). While there are many different factors that can contribute to unreliable findings in explanatory modeling, the combination of small-scale experiments involving noisy measurements and the (mis)use of null hypothesis significance testing (NHST) has received a great deal of attention in recent years. Under these conditions, researchers can mistake idiosyncratic patterns in noise for true effects, resulting in unreliable findings that do not replicate upon further investigation (Button et al., 2013; Loken and Gelman, 2017; Meehl, 1990; Simmons et al., 2011). More generally, some forms of data-dependent decision making (e.g., about how to define research questions or hypotheses, how to filter or transform data, how to model data, what tests to run, etc.) can lead to similar problems regardless of the specifics of the methods (Gelman and Loken, 2013). What about other fields, such as machine learning and data science, that focus less on explanation and more on predictive modeling, defined in Hofman et al. (2021) as directly forecasting outcomes (e.g., how well can an outcome Y be predicted using all available features X?) without necessarily focusing on isolating individual causal effects? Predictive modeling is typically done by testing (out-of-sample) predictions on large-scale datasets, and hence--unlike explanatory modeling--involves neither small experiments nor misuse of significance testing. With advances in the fields of statistics and machine learning (ML) we have seen remarkable performance gains in predictive modeling over the last decade, for both traditional ML tasks and for scientific applications. The same methods that have been shown to achieve at or above human-level performance on tasks like playing chess, classifying images, or understanding natural language (Zhang et al.,

The use of neural language models to model human behavior has met with mixed success. While some work has found that the surprisal estimates from these models can be used to predict a wide range of human neural and behavioral responses, other work studying more complex syntactic phenomena has found that these surprisal estimates generate incorrect behavioral predictions. This paper explores the extent to which the misalignment between empirical and model-predicted behavior can be minimized by training models on more developmentally plausible data, such as in the BabyLM Challenge. We trained teacher language models on the BabyLM "strict-small" dataset and used sentence level surprisal estimates from these teacher models to create a curriculum. We found tentative evidence that our curriculum made it easier for models to acquire linguistic knowledge from the training data: on the subset of tasks in the BabyLM challenge suite evaluating models' grammatical knowledge of English, models first trained on the BabyLM data curriculum and then on a few randomly ordered training epochs performed slightly better than models trained on randomly ordered epochs alone. This improved linguistic knowledge acquisition did not result in better alignment with human reading behavior, however: models trained on the BabyLM dataset (with or without a curriculum) generated predictions that were as misaligned with human behavior as models trained on larger less curated datasets. This suggests that training on developmentally plausible datasets alone is likely insufficient to generate language models capable of accurately predicting human language processing.