Parallel Attention and Feed-Forward Net Design for Pre-training and Inference on Transformers

In this paper, we introduce Parallel Attention and Feed-Forward Net Design (PAF) for transformer models. Transformer models are indisputably the backbone of all Natural Language Processing applications. Therefore, any efforts aimed at improving their efficiency are guaranteed to have an enormous impact. Transformer models consist of many layers and each layer has an attention block followed by a feed-forward network (FFN) that processes the input based on the attention block's output. We refer to this standard design as Series Attention and Feed-Forward Net Design (SAF). For each layer in our proposed PAF design for transformer models, we make FFN block's computations independent of the output of the attention block. This decoupling allows FFN block of each layer to run in parallel to the attention block of that layer. We evaluate PAF design by training two large language models (RoBERTa-large and bert-large-uncased) and comparing them to their SAF counterparts on six tasks of the General Language Understanding (GLUE) benchmark which test a multitude of semantic attributes. PAF models achieves nearly identical performance as their SAF counterparts on all the six tasks. We also compare time complexities of attention blocks with FFN blocks and find that running both blocks in parallel can theoretically and in practice achieve upto 1.5x to 2x gains in speed. We leave the development of fast and efficient libraries for implementation of PAF design for future work.

CLASS Meet SPOCK: An Education Tutoring Chatbot based on Learning Science Principles

We present a design framework called Conversational Learning with Analytical Step-by-Step Strategies (CLASS) for developing high-performance Intelligent Tutoring Systems (ITS). The CLASS framework aims to empower ITS with with two critical capabilities: imparting tutor-like step-by-step guidance and enabling tutor-like conversations in natural language to effectively engage learners. To empower ITS with the aforementioned capabilities, the CLASS framework employs two carefully curated synthetic datasets. The first scaffolding dataset encompasses a variety of elements, including problems, their corresponding subproblems, hints, incorrect solutions, and tailored feedback. This dataset provides ITS with essential problem-solving strategies necessary for guiding students through each step of the conversation. The second conversational dataset contains simulated student-tutor conversations that involve the application of problem-solving strategies learned from the first dataset. In the second dataset, the tutoring system adheres to a pre-defined response template, which helps to maintain consistency and structure in ITS's responses during its interactions. This structured methodology facilitates seamless integration of user feedback and yields valuable insights into ITS's internal decision-making process, allowing for continuous refinement and improvement of the system. We also present a proof-of-concept ITS, referred to as SPOCK, trained using the CLASS framework with a focus on college level introductory biology content. A carefully constructed protocol was developed for SPOCK's preliminary evaluation, examining aspects such as the factual accuracy and relevance of its responses. Experts in the field of biology offered favorable remarks, particularly highlighting SPOCK's capability to break down questions into manageable subproblems and provide step-by-step guidance to students.

WIRE: Wavelet Implicit Neural Representations

Implicit neural representations (INRs) have recently advanced numerous vision-related areas. INR performance depends strongly on the choice of the nonlinear activation function employed in its multilayer perceptron (MLP) network. A wide range of nonlinearities have been explored, but, unfortunately, current INRs designed to have high accuracy also suffer from poor robustness (to signal noise, parameter variation, etc.). Inspired by harmonic analysis, we develop a new, highly accurate and robust INR that does not exhibit this tradeoff. Wavelet Implicit neural REpresentation (WIRE) uses a continuous complex Gabor wavelet activation function that is well-known to be optimally concentrated in space-frequency and to have excellent biases for representing images. A wide range of experiments (image denoising, image inpainting, super-resolution, computed tomography reconstruction, image overfitting, and novel view synthesis with neural radiance fields) demonstrate that WIRE defines the new state of the art in INR accuracy, training time, and robustness.

MANER: Mask Augmented Named Entity Recognition for Extreme Low-Resource Languages

This paper investigates the problem of Named Entity Recognition (NER) for extreme low-resource languages with only a few hundred tagged data samples. NER is a fundamental task in Natural Language Processing (NLP). A critical driver accelerating NER systems' progress is the existence of large-scale language corpora that enable NER systems to achieve outstanding performance in languages such as English and French with abundant training data. However, NER for low-resource languages remains relatively unexplored. In this paper, we introduce Mask Augmented Named Entity Recognition (MANER), a new methodology that leverages the distributional hypothesis of pre-trained masked language models (MLMs) for NER. The <mask> token in pre-trained MLMs encodes valuable semantic contextual information. MANER re-purposes the <mask> token for NER prediction. Specifically, we prepend the <mask> token to every word in a sentence for which we would like to predict the named entity tag. During training, we jointly fine-tune the MLM and a new NER prediction head attached to each <mask> token. We demonstrate that MANER is well-suited for NER in low-resource languages; our experiments show that for 100 languages with as few as 100 training examples, it improves on state-of-the-art methods by up to 48% and by 12% on average on F1 score. We also perform detailed analyses and ablation studies to understand the scenarios that are best-suited to MANER.

Foveated Thermal Computational Imaging in the Wild Using All-Silicon Meta-Optics

Foveated imaging provides a better tradeoff between situational awareness (field of view) and resolution and is critical in long-wavelength infrared regimes because of the size, weight, power, and cost of thermal sensors. We demonstrate computational foveated imaging by exploiting the ability of a meta-optical frontend to discriminate between different polarization states and a computational backend to reconstruct the captured image/video. The frontend is a three-element optic: the first element which we call the "foveal" element is a metalens that focuses s-polarized light at a distance of $f_1$ without affecting the p-polarized light; the second element which we call the "perifoveal" element is another metalens that focuses p-polarized light at a distance of $f_2$ without affecting the s-polarized light. The third element is a freely rotating polarizer that dynamically changes the mixing ratios between the two polarization states. Both the foveal element (focal length = 150mm; diameter = 75mm), and the perifoveal element (focal length = 25mm; diameter = 25mm) were fabricated as polarization-sensitive, all-silicon, meta surfaces resulting in a large-aperture, 1:6 foveal expansion, thermal imaging capability. A computational backend then utilizes a deep image prior to separate the resultant multiplexed image or video into a foveated image consisting of a high-resolution center and a lower-resolution large field of view context. We build a first-of-its-kind prototype system and demonstrate 12 frames per second real-time, thermal, foveated image, and video capture in the wild.

Overfreezing Meets Overparameterization: A Double Descent Perspective on Transfer Learning of Deep Neural Networks

We study the generalization behavior of transfer learning of deep neural networks (DNNs). We adopt the overparameterization perspective -- featuring interpolation of the training data (i.e., approximately zero train error) and the double descent phenomenon -- to explain the delicate effect of the transfer learning setting on generalization performance. We study how the generalization behavior of transfer learning is affected by the dataset size in the source and target tasks, the number of transferred layers that are kept frozen in the target DNN training, and the similarity between the source and target tasks. We show that the test error evolution during the target DNN training has a more significant double descent effect when the target training dataset is sufficiently large with some label noise. In addition, a larger source training dataset can delay the arrival to interpolation and double descent peak in the target DNN training. Moreover, we demonstrate that the number of frozen layers can determine whether the transfer learning is effectively underparameterized or overparameterized and, in turn, this may affect the relative success or failure of learning. Specifically, we show that too many frozen layers may make a transfer from a less related source task better or on par with a transfer from a more related source task; we call this case overfreezing. We establish our results using image classification experiments with the residual network (ResNet) and vision transformer (ViT) architectures.

TITAN: Bringing The Deep Image Prior to Implicit Representations

We study the interpolation capabilities of implicit neural representations (INRs) of images. In principle, INRs promise a number of advantages, such as continuous derivatives and arbitrary sampling, being freed from the restrictions of a raster grid. However, empirically, INRs have been observed to poorly interpolate between the pixels of the fit image; in other words, they do not inherently possess a suitable prior for natural images. In this paper, we propose to address and improve INRs' interpolation capabilities by explicitly integrating image prior information into the INR architecture via deep decoder, a specific implementation of the deep image prior (DIP). Our method, which we call TITAN, leverages a residual connection from the input which enables integrating the principles of the grid-based DIP into the grid-free INR. Through super-resolution and computed tomography experiments, we demonstrate that our method significantly improves upon classic INRs, thanks to the induced natural image bias. We also find that by constraining the weights to be sparse, image quality and sharpness are enhanced, increasing the Lipschitz constant.

A Visual Tour Of Current Challenges In Multimodal Language Models

Transformer models trained on massive text corpora have become the de facto models for a wide range of natural language processing tasks. However, learning effective word representations for function words remains challenging. Multimodal learning, which visually grounds transformer models in imagery, can overcome the challenges to some extent; however, there is still much work to be done. In this study, we explore the extent to which visual grounding facilitates the acquisition of function words using stable diffusion models that employ multimodal models for text-to-image generation. Out of seven categories of function words, along with numerous subcategories, we find that stable diffusion models effectively model only a small fraction of function words -- a few pronoun subcategories and relatives. We hope that our findings will stimulate the development of new datasets and approaches that enable multimodal models to learn better representations of function words.

Batch Normalization Explained

A critically important, ubiquitous, and yet poorly understood ingredient in modern deep networks (DNs) is batch normalization (BN), which centers and normalizes the feature maps. To date, only limited progress has been made understanding why BN boosts DN learning and inference performance; work has focused exclusively on showing that BN smooths a DN's loss landscape. In this paper, we study BN theoretically from the perspective of function approximation; we exploit the fact that most of today's state-of-the-art DNs are continuous piecewise affine (CPA) splines that fit a predictor to the training data via affine mappings defined over a partition of the input space (the so-called "linear regions"). {\em We demonstrate that BN is an unsupervised learning technique that -- independent of the DN's weights or gradient-based learning -- adapts the geometry of a DN's spline partition to match the data.} BN provides a "smart initialization" that boosts the performance of DN learning, because it adapts even a DN initialized with random weights to align its spline partition with the data. We also show that the variation of BN statistics between mini-batches introduces a dropout-like random perturbation to the partition boundaries and hence the decision boundary for classification problems. This per mini-batch perturbation reduces overfitting and improves generalization by increasing the margin between the training samples and the decision boundary.

Momentum Transformer: Closing the Performance Gap Between Self-attention and Its Linearization

Transformers have achieved remarkable success in sequence modeling and beyond but suffer from quadratic computational and memory complexities with respect to the length of the input sequence. Leveraging techniques include sparse and linear attention and hashing tricks; efficient transformers have been proposed to reduce the quadratic complexity of transformers but significantly degrade the accuracy. In response, we first interpret the linear attention and residual connections in computing the attention map as gradient descent steps. We then introduce momentum into these components and propose the \emph{momentum transformer}, which utilizes momentum to improve the accuracy of linear transformers while maintaining linear memory and computational complexities. Furthermore, we develop an adaptive strategy to compute the momentum value for our model based on the optimal momentum for quadratic optimization. This adaptive momentum eliminates the need to search for the optimal momentum value and further enhances the performance of the momentum transformer. A range of experiments on both autoregressive and non-autoregressive tasks, including image generation and machine translation, demonstrate that the momentum transformer outperforms popular linear transformers in training efficiency and accuracy.