In agriculture, Abdoulaye Baniré Diallo, co-founder and chief scientific officer of the AI startup My Intelligent Machines, is working with advanced algorithms and machine learning methods to leverage genomic precision in livestock production models. With genomic precision, it is possible to build intelligent breeding programs that minimize the ecological footprint, address changing consumer demands, and contribute to the well-being of people and animals alike through the selection of good genetic characteristics at an early stage of the livestock production process. These are just a few examples that illustrate the transformative potential of AI technology in Africa.
Man With Machine: Harnessing the Potential of Artificial Intelligence
The advances in artificial intelligence that are transforming many fields have yet to make an impact in hearing. Hearing healthcare continues to rely on a labour-intensive service model that fails to provide access to the majority of those in need, while hearing research suffers from a lack of computational tools with the capacity to match the complexities of auditory processing. This Perspective is a call for the artificial intelligence and hearing communities to come together to bring about a technological revolution in hearing. We describe opportunities for rapid clinical impact through the application of existing technologies and propose directions for the development of new technologies to create true artificial auditory systems. There is an urgent need to push hearing towards a future in which artificial intelligence provides critical support for the testing of hypotheses, the development of therapies and the effective delivery of care worldwide.
Recent advances in artificial intelligence (AI) have the potential to transform hearing. Machines have already achieved human-like performance in important hearing-related tasks such as automatic speech recognition (ASR)4,5 and natural language processing6,7. AI is also starting to have an impact in medicine; for example, eye screening technologies based on deep neural networks (DNNs) are already in worldwide use. But there are few applications related to hearing per se, and AI remains absent from hearing healthcare. In this Perspective, we describe opportunities to use existing technologies to create clinical applications with widespread impact, as well as the potential for new technologies that faithfully model the auditory system to enable fundamental advances in hearing research.
The recent incorporation of DNNs into machine hearing systems has further improved their performance in specific tasks, but it has not brought machine hearing any closer to the auditory system in a mechanistic sense. Biological replication is not necessarily a requirement: many of the important clinical challenges in hearing can be addressed using models with no relation to the auditory system11 (for example, DNNs for image classification) or models that mimic only certain aspects of its function12,13 (such as DNNs for sound source separation). But for the full potential of AI in hearing to be realized, new machine hearing systems that match both the function of the auditory system and key elements of its structure are needed.
The auditory system is a marvel of signal processing. Its combination of microsecond temporal precision, sensitivity over more than five orders of sound magnitude and flexibility to support tasks ranging from sound localization to music appreciation is still without parallel in other natural or artificial systems. This remarkable performance is achieved through a complex interplay of biomechanical, chemical and neural components that implement operations such as signal conditioning, filtering, feature extraction and classification in interconnected stages across the ear and brain to create the experience of auditory perception (Fig. 1a).
The challenge in designing automated audiogram measurement applications is that neither the specifics of the equipment nor the environment can be guaranteed in a non-clinical setting25. AI can potentially help by framing the problem as audiogram inference rather than audiogram measurement. Given a sufficient training dataset of paired audiograms measured under ideal and non-ideal conditions (perhaps supplemented by data augmentation), along with calibration routines to determine background noise levels, earphone properties and so on, it should be possible to infer the true audiogram from non-ideal measurements.
Supporting alternative modes of unstructured social communication is more challenging, as many deaf people communicate through signed, rather than spoken, language. But technologies for real-time automated translation can potentially bridge this gap. One recent study demonstrated the potential for a glove-like device that tracks finger movements to enable translation from American sign language to English94. This technology required the coordinated development of hardware that is comfortable, durable and flexible, and associated software to classify signals from the device using support vector machines. Although the overall accuracy of the system in this initial study was 98%, the vocabulary was limited to only 11 gestures, so more work is needed to enable use of the full complement of gestures, as well as integration with facial and other movements. Applications based on such technology have the potential to support natural communication not only between deaf people and hearing people, but also between deaf people from different countries, each of which has its own unique signed language.
The difficulties associated with complex hearing disorders stem from the fact that they are emergent properties of aberrant network states (as opposed to consequences of identifiable molecular or cellular pathologies). Current technologies for regression and classification may be able to improve care for these disorders by identifying reliable biomarkers or other objective measures within complex data to allow more accurate diagnosis and treatment52,53. But a more ambitious approach is for AI researchers and hearing researchers to work together to create new artificial networks for hearing that share key mechanistic features with the auditory system.
If an artificial system is to serve as a surrogate for testing manipulations that cannot be performed on the auditory system itself (either at all, or at the required scale), biological replication will help to ensure that any conclusions drawn from observations made in silico will also hold true in vivo. Artificial auditory systems could provide a powerful framework for the generation and testing of new hypotheses and could serve as a platform for developing potential treatments for network-level disorders54. In the following sections, we highlight three critical aspects of hearing that artificial auditory systems will need to incorporate: temporal processing, multi-modal processing, and plasticity.
To accurately model the auditory system, artificial networks must ultimately integrate other sensorimotor modalities with the flexibility to perform a wide range of different tasks just as the brain does66. The ears are just one of many sources that provide information to the brain, and the integration of information from different sources is evident even at early stages of processing67. Explicit attempts to model multi-modal properties in isolation are unlikely to be useful (beyond providing a compact description of the phenomena). But if networks with appropriate features are trained on a wide variety of tasks, multi-modal flexibility will emerge, just as it has in the brain.
Despite the potential for AI to produce dramatic improvements, it has yet to make a substantial impact. We have described opportunities for AI to reshape hearing healthcare with the potential for immediate benefit on the diagnosis and treatment of many common conditions. For this potential to be realized, coordinated effort is required, with AI developers working to turn current technologies into robust applications, and hearing scientists and clinicians ensuring both the availability of appropriate data for training and responsive clinical infrastructure to support rapid adoption.
We have also outlined ways in which AI could be applied beyond healthcare to play a critical part in future hearing research. Artificial networks that provide accurate models of auditory processing, with parallel computations across multiple timescales, integration of inputs from multiple modalities and plasticity to adapt to internal and external changes, have the potential to revolutionize the study of hearing. But to realize this potential, AI researchers and hearing researchers must work together to coordinate experiments on artificial networks and the auditory system with the goal of identifying the aspects of structure and function that are most important.
BCIsg are policies, activities, services or products designed to induce or support people to act differently from how they would have acted otherwise. They involve attempting to change either characteristics of members of the target population (in terms of their knowledge, skills, beliefs, feelings or habits), or their social or physical environment, or both. In the large majority of cases, the goal is to achieve change that is sustained over an extended period of time (e.g., reducing excessive alcohol consumption or smoking prevalence in the general population, or fostering new prescribing patterns among clinicians). Research findings have the potential to provide invaluable knowledge to help with developing or selecting BCIs but this evidence needs to be synthesised and interpreted. We need a cumulative, contemporaneous and accessible knowledge baseg of behaviour change findings to continue to build the science of human behaviour change.
Artificial intelligence (AIg) and machine learning (MLg) applications have been developed to generate and interrogate large, accumulating knowledge bases using ontological approaches. In the HBCP, building computer programs to extract and process knowledge from text documents at a level that is usable by experts in the domain, requires several elements that can generally be equated with intelligence, such as advanced reading ability and significant domain understanding. In this respect, a computer program performing this task can be thought of as artificially intelligent. 2ff7e9595c
Comentários