Despite the significant advances achieved in Artificial Neural Networks (ANNs), their design process remains notoriously tedious, depending primarily on intuition, experience and trial-and-error. This human-dependent process is often time-consuming and prone to errors. Furthermore, the models are generally bound to their training contexts, with no considerations to their surrounding environments. Continual adaptiveness and automation of neural networks is of paramount importance to several domains where model accessibility is limited after deployment (e.g IoT devices, self-driving vehicles, etc.). Additionally, even accessible models require frequent maintenance post-deployment to overcome issues such as Concept/Data Drift, which can be cumbersome and restrictive. By leveraging and combining approaches from Neural Architecture Search (NAS) and Continual Learning (CL), more robust and adaptive agents can be developed. This study conducts the first extensive review on the intersection between NAS and CL, formalizing the prospective Continually-Adaptive Neural Networks (CANNs) paradigm and outlining research directions for lifelong autonomous ANNs.

Automated scoring of open-ended student responses has the potential to significantly reduce human grader effort. Recent advances in automated scoring often leverage textual representations based on pre-trained language models such as BERT and GPT as input to scoring models. Most existing approaches train a separate model for each item/question, which is suitable for scenarios such as essay scoring where items can be quite different from one another. However, these approaches have two limitations: 1) they fail to leverage item linkage for scenarios such as reading comprehension where multiple items may share a reading passage; 2) they are not scalable since storing one model per item becomes difficult when models have a large number of parameters. In this paper, we report our (grand prize-winning) solution to the National Assessment of Education Progress (NAEP) automated scoring challenge for reading comprehension. Our approach, in-context BERT fine-tuning, produces a single shared scoring model for all items with a carefully-designed input structure to provide contextual information on each item. We demonstrate the effectiveness of our approach via local evaluations using the training dataset provided by the challenge. We also discuss the biases, common error types, and limitations of our approach.

Likelihood is a standard estimate for outlier detection. The specific role of the normalization constraint is to ensure that the out-of-distribution (OOD) regime has a small likelihood when samples are learned using maximum likelihood. Because autoencoders do not possess such a process of normalization, they often fail to recognize outliers even when they are obviously OOD. We propose the Normalized Autoencoder (NAE), a normalized probabilistic model constructed from an autoencoder. The probability density of NAE is defined using the reconstruction error of an autoencoder, which is differently defined in the conventional energy-based model. In our model, normalization is enforced by suppressing the reconstruction of negative samples, significantly improving the outlier detection performance. Our experimental results confirm the efficacy of NAE, both in detecting outliers and in generating in-distribution samples.

Consider a teenager, Jorge, who is caught possessing a large amount of marijuana by a school administrator and will be expelled if he's reported to his parole officer. If the administrator does not report him, they're breaking the law; if they do, they're condemning him to one of the worst schools in the city and likely recidivism. This is a case study we presented to a class of 60 students at the Harvard Graduate School of Education. We asked them to pretend to be a teacher or administrator at the school and design a course of action. One hour into their conversation, we presented them with ChatGPT's analysis of the study.

Knowledge Distillation (KD) is a promising technique for reducing the high computational demand of large language models (LLMs). However, previous KD methods are primarily applied to white-box classification models or training small models to imitate black-box model APIs like ChatGPT. How to effectively distill the knowledge from white-box generative LLMs is still under-explored, which becomes more and more important with the prosperity of LLMs. In this work, we propose MiniLLM that distills smaller language models from generative larger language models. We first replace the forward Kullback-Leibler divergence (KLD) objective in the standard KD approaches with reverse KLD, which is more suitable for KD on generative language models, to prevent the student model from overestimating the low-probability regions of the teacher distribution. Then, we derive an effective optimization approach to learn this objective. Extensive experiments in the instruction-following setting show that the MiniLLM models generate more precise responses with the higher overall quality, lower exposure bias, better calibration, and higher long-text generation performance. Our method is also scalable for different model families with 120M to 13B parameters. We will release our code and model checkpoints at https://aka.ms/MiniLLM.

This paper explores educational interactions involving humans and artificial intelligences not as sequences of prompts and responses, but as a social process of conversation and exploration. In this conception, learners continually converse with AI language models within a dynamic computational medium of internet tools and resources. Learning happens when this distributed system sets goals, builds meaning from data, consolidates understanding, reconciles differences, and transfers knowledge to new domains. Building social generative AI for education will require development of powerful AI systems that can converse with each other as well as humans, construct external representations such as knowledge maps, access and contribute to internet resources, and act as teachers, learners, guides and mentors. This raises fundamental problems of ethics. Such systems should be aware of their limitations, their responsibility to learners and the integrity of the internet, and their respect for human teachers and experts. We need to consider how to design and constrain social generative AI for education.

Building a theoretical understanding of the capabilities of large language models (LLMs) is vital for our ability to predict and explain the behavior of these systems. Here, we investigate the structure of LLM capabilities by extracting latent capabilities from patterns of individual differences across a varied population of LLMs. Using a combination of Bayesian and frequentist factor analysis, we analyzed data from 29 different LLMs across 27 cognitive tasks. We found evidence that LLM capabilities are not monolithic. Instead, they are better explained by three well-delineated factors that represent reasoning, comprehension and core language modeling. Moreover, we found that these three factors can explain a high proportion of the variance in model performance. These results reveal a consistent structure in the capabilities of different LLMs and demonstrate the multifaceted nature of these capabilities. We also found that the three abilities show different relationships to model properties such as model size and instruction tuning. These patterns help refine our understanding of scaling laws and indicate that changes to a model that improve one ability might simultaneously impair others. Based on these findings, we suggest that benchmarks could be streamlined by focusing on tasks that tap into each broad model ability.

We introduce EM-Network, a novel self-distillation approach that effectively leverages target information for supervised sequence-to-sequence (seq2seq) learning. In contrast to conventional methods, it is trained with oracle guidance, which is derived from the target sequence. Since the oracle guidance compactly represents the target-side context that can assist the sequence model in solving the task, the EM-Network achieves a better prediction compared to using only the source input. To allow the sequence model to inherit the promising capability of the EM-Network, we propose a new self-distillation strategy, where the original sequence model can benefit from the knowledge of the EM-Network in a one-stage manner. We conduct comprehensive experiments on two types of seq2seq models: connectionist temporal classification (CTC) for speech recognition and attention-based encoder-decoder (AED) for machine translation. Experimental results demonstrate that the EM-Network significantly advances the current state-of-the-art approaches, improving over the best prior work on speech recognition and establishing state-of-the-art performance on WMT'14 and IWSLT'14.

Aquaculture systems can benefit from the recent development of advanced control strategies to reduce operating costs and fish loss and increase growth production efficiency, resulting in fish welfare and health. Monitoring the water quality and controlling feeding are fundamental elements of balancing fish productivity and shaping the fish growth process. Currently, most fish-feeding processes are conducted manually in different phases and rely on time-consuming and challenging artificial discrimination. The feeding control approach influences fish growth and breeding through the feed conversion rate; hence, controlling these feeding parameters is crucial for enhancing fish welfare and minimizing general fishery costs. The high concentration of environmental factors, such as a high ammonia concentration and pH, affect the water quality and fish survival. Therefore, there is a critical need to develop control strategies to determine optimal, efficient, and reliable feeding processes and monitor water quality. This paper reviews the main control design techniques for fish growth in aquaculture systems, namely algorithms that optimize the feeding and water quality of a dynamic fish growth process. Specifically, we review model-based control approaches and model-free reinforcement learning strategies to optimize the growth and survival of the fish or track a desired reference live-weight growth trajectory. The model-free framework uses an approximate fish growth dynamic model and does not satisfy constraints. We discuss how model-based approaches can support a reinforcement learning framework to efficiently handle constraint satisfaction and find better trajectories and policies from value-based reinforcement learning.

Text Classification is one of the fundamental tasks in natural language processing, which requires an agent to determine the most appropriate category for input sentences. Recently, deep neural networks have achieved impressive performance in this area, especially Pre-trained Language Models (PLMs). Usually, these methods concentrate on input sentences and corresponding semantic embedding generation. However, for another essential component: labels, most existing works either treat them as meaningless one-hot vectors or use vanilla embedding methods to learn label representations along with model training, underestimating the semantic information and guidance that these labels reveal. To alleviate this problem and better exploit label information, in this paper, we employ Self-Supervised Learning (SSL) in model learning process and design a novel self-supervised Relation of Relation (R2) classification task for label utilization from a one-hot manner perspective. Then, we propose a novel Relation of Relation Learning Network (R2-Net) for text classification, in which text classification and R2 classification are treated as optimization targets. Meanwhile, triplet loss is employed to enhance the analysis of differences and connections among labels. Moreover, considering that one-hot usage is still short of exploiting label information, we incorporate external knowledge from WordNet to obtain multi-aspect descriptions for label semantic learning and extend R2-Net to a novel Description-Enhanced Label Embedding network (DELE) from a label embedding perspective. ...