Relating dynamic brain states to dynamic machine states: Human and machine solutions to the speech recognition problem

Machine learning in Alzheimer's disease drug discovery and target identification

Alzheimer's disease (AD) stands as a formidable neurodegenerative ailment that poses a substantial threat to the elderly population, with no known curative or disease-slowing drugs in existence. Among the vital and time-consuming stages in the drug discovery process, disease modeling and target identification hold particular significance. Disease modeling allows for a deeper comprehension of disease progression mechanisms and potential therapeutic avenues. On the other hand, target identification serves as the foundational step in drug development, exerting a profound influence on all subsequent phases and ultimately determining the success rate of drug development endeavors. Machine learning (ML) techniques have ushered in transformative breakthroughs in the realm of target discovery. Leveraging the strengths of large dataset analysis, multifaceted data processing, and the exploration of intricate biological mechanisms, ML has become instrumental in the quest for effective AD treatments. In this comprehensive review, we offer an account of how ML methodologies are being deployed in the pursuit of drug discovery for AD. Furthermore, we provide an overview of the utilization of ML in uncovering potential intervention strategies and prospective therapeutic targets for AD. Finally, we discuss the principal challenges and limitations currently faced by these approaches. We also explore the avenues for future research that hold promise in addressing these challenges.

On the similarities of representations in artificial and brain neural networks for speech recognition

Introduction

In recent years, machines powered by deep learning have achieved near-human levels of performance in speech recognition. The fields of artificial intelligence and cognitive neuroscience have finally reached a similar level of performance, despite their huge differences in implementation, and so deep learning models can-in principle-serve as candidates for mechanistic models of the human auditory system.

Methods

Utilizing high-performance automatic speech recognition systems, and advanced non-invasive human neuroimaging technology such as magnetoencephalography and multivariate pattern-information analysis, the current study aimed to relate machine-learned representations of speech to recorded human brain representations of the same speech.

Results

In one direction, we found a quasi-hierarchical functional organization in human auditory cortex qualitatively matched with the hidden layers of deep artificial neural networks trained as part of an automatic speech recognizer. In the reverse direction, we modified the hidden layer organization of the artificial neural network based on neural activation patterns in human brains. The result was a substantial improvement in word recognition accuracy and learned speech representations.

Discussion

We have demonstrated that artificial and brain neural networks can be mutually informative in the domain of speech recognition.

Screening for cardiac contractile dysfunction using an artificial intelligence-enabled electrocardiogram

Asymptomatic left ventricular dysfunction (ALVD) is present in 3-6% of the general population, is associated with reduced quality of life and longevity, and is treatable when found^1-4. An inexpensive, noninvasive screening tool for ALVD in the doctor's office is not available. We tested the hypothesis that application of artificial intelligence (AI) to the electrocardiogram (ECG), a routine method of measuring the heart's electrical activity, could identify ALVD. Using paired 12-lead ECG and echocardiogram data, including the left ventricular ejection fraction (a measure of contractile function), from 44,959 patients at the Mayo Clinic, we trained a convolutional neural network to identify patients with ventricular dysfunction, defined as ejection fraction ≤35%, using the ECG data alone. When tested on an independent set of 52,870 patients, the network model yielded values for the area under the curve, sensitivity, specificity, and accuracy of 0.93, 86.3%, 85.7%, and 85.7%, respectively. In patients without ventricular dysfunction, those with a positive AI screen were at 4 times the risk (hazard ratio, 4.1; 95% confidence interval, 3.3 to 5.0) of developing future ventricular dysfunction compared with those with a negative screen. Application of AI to the ECG-a ubiquitous, low-cost test-permits the ECG to serve as a powerful screening tool in asymptomatic individuals to identify ALVD.

Balancing Prediction and Sensory Input in Speech Comprehension: The Spatiotemporal Dynamics of Word Recognition in Context

Spoken word recognition in context is remarkably fast and accurate, with recognition times of ∼200 ms, typically well before the end of the word. The neurocomputational mechanisms underlying these contextual effects are still poorly understood. This study combines source-localized electroencephalographic and magnetoencephalographic (EMEG) measures of real-time brain activity with multivariate representational similarity analysis to determine directly the timing and computational content of the processes evoked as spoken words are heard in context, and to evaluate the respective roles of bottom-up and predictive processing mechanisms in the integration of sensory and contextual constraints. Male and female human participants heard simple (modifier-noun) English phrases that varied in the degree of semantic constraint that the modifier (W1) exerted on the noun (W2), as in pairs, such as "yellow banana." We used gating tasks to generate estimates of the probabilistic predictions generated by these constraints as well as measures of their interaction with the bottom-up perceptual input for W2. Representation similarity analysis models of these measures were tested against electroencephalographic and magnetoencephalographic brain data across a bilateral fronto-temporo-parietal language network. Consistent with probabilistic predictive processing accounts, we found early activation of semantic constraints in frontal cortex (LBA45) as W1 was heard. The effects of these constraints (at 100 ms after W2 onset in left middle temporal gyrus and at 140 ms in left Heschl's gyrus) were only detectable, however, after the initial phonemes of W2 had been heard. Within an overall predictive processing framework, bottom-up sensory inputs are still required to achieve early and robust spoken word recognition in context.SIGNIFICANCE STATEMENT Human listeners recognize spoken words in natural speech contexts with remarkable speed and accuracy, often identifying a word well before all of it has been heard. In this study, we investigate the brain systems that support this important capacity, using neuroimaging techniques that can track real-time brain activity during speech comprehension. This makes it possible to locate the brain areas that generate predictions about upcoming words and to show how these expectations are integrated with the evidence provided by the speech being heard. We use the timing and localization of these effects to provide the most specific account to date of how the brain achieves an optimal balance between prediction and sensory input in the interpretation of spoken language.