Similarresultshavealsobeen observedinthe VGG-16 architecture (see Supplementary Materials SectionF).

Large language models (LLMs) are increasingly attracting the attention of healthcare professionals for their potential to assist in diagnostic assessments, which could alleviate the strain on the healthcare system caused by a high patient load and a shortage of providers. For LLMs to be effective in supporting diagnostic assessments, it is essential that they closely replicate the standard diagnostic procedures used by clinicians. In this paper, we specifically examine the diagnostic assessment processes described in the Patient Health Questionnaire-9 (PHQ-9) for major depressive disorder (MDD) and the Generalized Anxiety Disorder-7 (GAD-7) questionnaire for generalized anxiety disorder (GAD). We investigate various prompting and fine-tuning techniques to guide both proprietary and open-source LLMs in adhering to these processes, and we evaluate the agreement between LLM-generated diagnostic outcomes and expert-validated ground truth. For fine-tuning, we utilize the Mentalllama and Llama models, while for prompting, we experiment with proprietary models like GPT-3.5 and GPT-4o, as well as open-source models such as llama-3.1-8b and mixtral-8x7b.

Compressed video action recognition classifies video samples by leveraging the different modalities in compressed videos, namely motion vectors, residuals, and intra-frames. For this purpose, three neural networks are deployed, each dedicated to processing one modality. Our observations indicate that the network processing intra-frames tend to converge to a flatter minimum than the network processing residuals, which in turn converges to a flatter minimum than the motion vector network. This hierarchy in convergence motivates our strategy for knowledge transfer among modalities to achieve flatter minima, which are generally associated with better generalization. With this insight, we propose Progressive Knowledge Distillation (PKD), a technique that incrementally transfers knowledge across the modalities. This method involves attaching early exits (Internal Classifiers - ICs) to the three networks. PKD distills knowledge starting from the motion vector network, followed by the residual, and finally, the intra-frame network, sequentially improving IC accuracy. Further, we propose the Weighted Inference with Scaled Ensemble (WISE), which combines outputs from the ICs using learned weights, boosting accuracy during inference. Our experiments demonstrate the effectiveness of training the ICs with PKD compared to standard cross-entropy-based training, showing IC accuracy improvements of up to 5.87% and 11.42% on the UCF-101 and HMDB-51 datasets, respectively. Additionally, WISE improves accuracy by up to 4.28% and 9.30% on UCF-101 and HMDB-51, respectively.

Spiking Neural Networks (SNNs) that operate in an event-driven manner and employ binary spike representation have recently emerged as promising candidates for energy-efficient computing. However, a cost bottleneck arises in obtaining high-performance SNNs: training a SNN model requires a large number of time steps in addition to the usual learning iterations, hence this limits their energy efficiency. This paper proposes a general training framework that enhances feature learning and activation efficiency within a limited time step, providing a new solution for more energy-efficient SNNs. Our framework allows SNN neurons to learn robust spike feature from different receptive fields and update neuron states by utilizing both current stimuli and recurrence information transmitted from other neurons. This setting continuously complements information within a single time step. Additionally, we propose a projection function to merge these two stimuli to smoothly optimize neuron weights (spike firing threshold and activation). We evaluate the proposal for both convolution and recurrent models. Our experimental results indicate state-of-the-art visual classification tasks, including CIFAR10, CIFAR100, and TinyImageNet.Our framework achieves 72.41% and 72.31% top-1 accuracy with only 1 time step on CIFAR100 for CNNs and RNNs, respectively. Our method reduces 10x and 3x joule energy than a standard ANN and SNN, respectively, on CIFAR10, without additional time steps.

Large Language Models (LLMs) encode meanings of words in the form of distributed semantics. Distributed semantics capture common statistical patterns among language tokens (words, phrases, and sentences) from large amounts of data. LLMs perform exceedingly well across General Language Understanding Evaluation (GLUE) tasks designed to test a model's understanding of the meanings of the input tokens. However, recent studies have shown that LLMs tend to generate unintended, inconsistent, or wrong texts as outputs when processing inputs that were seen rarely during training, or inputs that are associated with diverse contexts (e.g., well-known hallucination phenomenon in language generation tasks). Crowdsourced and expert-curated knowledge graphs such as ConceptNet are designed to capture the meaning of words from a compact set of well-defined contexts. Thus LLMs may benefit from leveraging such knowledge contexts to reduce inconsistencies in outputs. We propose a novel ensemble learning method, Interpretable Ensemble Representation Learning (IERL), that systematically combines LLM and crowdsourced knowledge representations of input tokens. IERL has the distinct advantage of being interpretable by design (when was the LLM context used vs. when was the knowledge context used?) over state-of-the-art (SOTA) methods, allowing scrutiny of the inputs in conjunction with the parameters of the model, facilitating the analysis of models' inconsistent or irrelevant outputs. Although IERL is agnostic to the choice of LLM and crowdsourced knowledge, we demonstrate our approach using BERT and ConceptNet. We report improved or competitive results with IERL across GLUE tasks over current SOTA methods and significantly enhanced model interpretability.

Domain-specific language understanding requires integrating multiple pieces of relevant contextual information. For example, we see both suicide and depression-related behavior (multiple contexts) in the text ``I have a gun and feel pretty bad about my life, and it wouldn't be the worst thing if I didn't wake up tomorrow''. Domain specificity in self-attention architectures is handled by fine-tuning on excerpts from relevant domain specific resources (datasets and external knowledge - medical textbook chapters on mental health diagnosis related to suicide and depression). We propose a modified self-attention architecture Knowledge-infused Self Attention Transformer (KSAT) that achieves the integration of multiple domain-specific contexts through the use of external knowledge sources. KSAT introduces knowledge-guided biases in dedicated self-attention layers for each knowledge source to accomplish this. In addition, KSAT provides mechanics for controlling the trade-off between learning from data and learning from knowledge. Our quantitative and qualitative evaluations show that (1) the KSAT architecture provides novel human-understandable ways to precisely measure and visualize the contributions of the infused domain contexts, and (2) KSAT performs competitively with other knowledge-infused baselines and significantly outperforms baselines that use fine-tuning for domain-specific tasks.

Transformer-based language models have achieved impressive success in various natural language processing tasks due to their ability to capture complex dependencies and contextual information using self-attention mechanisms. However, they are not without limitations. These limitations include hallucinations, where they produce incorrect outputs with high confidence, and alignment issues, where they generate unhelpful and unsafe outputs for human users. These limitations stem from the absence of implicit and missing context in the data alone. To address this, researchers have explored augmenting these models with external knowledge from knowledge graphs to provide the necessary additional context. However, the ad-hoc nature of existing methods makes it difficult to properly analyze the effects of knowledge infusion on the many moving parts or components of a transformer. This paper introduces a systematic method for infusing knowledge into different components of a transformer-based model. A modular framework is proposed to identify specific components within the transformer architecture, such as the self-attention mechanism, encoder layers, or the input embedding layer, where knowledge infusion can be applied. Additionally, extensive experiments are conducted on the General Language Understanding Evaluation (GLUE) benchmark tasks, and the findings are reported. This systematic approach aims to facilitate more principled approaches to incorporating knowledge into language model architectures.

Event-based cameras offer a low-power alternative to frame-based cameras for capturing high-speed motion and high dynamic range scenes. They provide asynchronous streams of sparse events. Spiking Neural Networks (SNNs) with their asynchronous event-driven compute, show great potential for extracting the spatio-temporal features from these event streams. In contrast, the standard Analog Neural Networks (ANNs1) fail to process event data effectively. However, training SNNs is difficult due to additional trainable parameters (thresholds and leaks), vanishing spikes at deeper layers, non-differentiable binary activation function etc. Moreover, an additional data structure "membrane potential" responsible for keeping track of temporal information, must be fetched and updated at every timestep in SNNs. To overcome these, we propose a novel SNN-ANN hybrid architecture that combines the strengths of both. Specifically, we leverage the asynchronous compute capabilities of SNN layers to effectively extract the input temporal information. While the ANN layers offer trouble-free training and implementation on standard machine learning hardware such as GPUs. We provide extensive experimental analysis for assigning each layer to be spiking or analog in nature, leading to a network configuration optimized for performance and ease of training. We evaluate our hybrid architectures for optical flow estimation using event-data on DSEC-flow and Mutli-Vehicle Stereo Event-Camera (MVSEC) datasets. The results indicate that our configured hybrid architectures outperform the state-of-the-art ANN-only, SNN-only and past hybrid architectures both in terms of accuracy and efficiency. Specifically, our hybrid architecture exhibit a 31% and 24.8% lower average endpoint error (AEE) at 2.1x and 3.1x lower energy, compared to an SNN-only architecture on DSEC and MVSEC datasets, respectively.

Current Virtual Mental Health Assistants (VMHAs) provide counseling and suggestive care. They refrain from patient diagnostic assistance because they lack training in safety-constrained and specialized clinical process knowledge. In this work, we define Proknow as an ordered set of information that maps to evidence-based guidelines or categories of conceptual understanding to experts in a domain. We also introduce a new dataset of diagnostic conversations guided by safety constraints and Proknow that healthcare professionals use. We develop a method for natural language question generation (NLG) that collects diagnostic information from the patient interactively. We demonstrate the limitations of using state-of-the-art large-scale language models (LMs) on this dataset. Our algorithm models the process knowledge through explicitly modeling safety, knowledge capture, and explainability. LMs augmented with ProKnow guided method generated 89% safer questions in the depression and anxiety domain. The Explainability of the generated question is assessed by computing similarity with concepts in depression and anxiety knowledge bases. Overall, irrespective of the type of LMs augmented with our ProKnow, we achieved an average 82% improvement over simple pre-trained LMs on safety, explainability, and process-guided question generation. We qualitatively and quantitatively evaluate the efficacy of the proposed ProKnow-guided methods by introducing three new evaluation metrics for safety, explainability, and process knowledge adherence.

WHAT: Computers are gradually thinking like humans thanks to the development of artificial intelligence networks capable of learning on their own, called "deep learning." These networks can already recognize images and play chess, for example. But in comparison to the human brain, deep learning can require up to 1,000 times more energy to perform the same functions. This means that if smart glasses used deep learning to recognize objects, the battery would last only 25 minutes, studies have shown. In a perspective paper published in Nature, Purdue University researchers recommend that deep-learning networks mimic electrical signals in the brain, called "spikes," to be more energy efficient.