Rajeev Rikhye
YOU?
Author Swipe
View article: Closing the AI generalisation gap by adjusting for dermatology condition distribution differences across clinical settings
Closing the AI generalisation gap by adjusting for dermatology condition distribution differences across clinical settings Open
View article: Closing the AI generalization gap by adjusting for dermatology condition distribution differences across clinical settings
Closing the AI generalization gap by adjusting for dermatology condition distribution differences across clinical settings Open
Recently, there has been great progress in the ability of artificial intelligence (AI) algorithms to classify dermatological conditions from clinical photographs. However, little is known about the robustness of these algorithms in real-wo…
View article: Differences Between Patient and Clinician-Taken Images: Implications for Virtual Care of Skin Conditions
Differences Between Patient and Clinician-Taken Images: Implications for Virtual Care of Skin Conditions Open
There are various demographic, clinical, and image quality characteristic differences between PAT and CLIN photographs of skin concerns. The demographic characteristic differences present important considerations for improving digital lite…
View article: Evaluating AI systems under uncertain ground truth: a case study in dermatology
Evaluating AI systems under uncertain ground truth: a case study in dermatology Open
For safety, medical AI systems undergo thorough evaluations before deployment, validating their predictions against a ground truth which is assumed to be fixed and certain. However, this ground truth is often curated in the form of differe…
View article: Personal VAD 2.0: Optimizing Personal Voice Activity Detection for On-Device Speech Recognition
Personal VAD 2.0: Optimizing Personal Voice Activity Detection for On-Device Speech Recognition Open
Personalization of on-device speech recognition (ASR) has seen explosive growth in recent years, largely due to the increasing popularity of personal assistant features on mobile devices and smart home speakers. In this work, we present Pe…
View article: Closing the Gap between Single-User and Multi-User VoiceFilter-Lite
Closing the Gap between Single-User and Multi-User VoiceFilter-Lite Open
VoiceFilter-Lite is a speaker-conditioned voice separation model that plays a crucial role in improving speech recognition and speaker verification by suppressing overlapping speech from non-target speakers. However, one limitation of Voic…
View article: Multi-User Voicefilter-Lite via Attentive Speaker Embedding
Multi-User Voicefilter-Lite via Attentive Speaker Embedding Open
In this paper, we propose a solution to allow speaker conditioned speech models, such as VoiceFilter-Lite, to support an arbitrary number of enrolled users in a single pass. This is achieved by using an attention mechanism on multiple spea…
View article: Reliable Sensory Processing in Mouse Visual Cortex through Cooperative Interactions between Somatostatin and Parvalbumin Interneurons
Reliable Sensory Processing in Mouse Visual Cortex through Cooperative Interactions between Somatostatin and Parvalbumin Interneurons Open
Intrinsic neuronal variability significantly limits information encoding in the primary visual cortex (V1). However, under certain conditions, neurons can respond reliably with highly precise responses to the same visual stimuli from trial…
View article: Personalized Keyphrase Detection Using Speaker and Environment Information
Personalized Keyphrase Detection Using Speaker and Environment Information Open
In this paper, we introduce a streaming keyphrase detection system that can be easily customized to accurately detect any phrase composed of words from a large vocabulary. The system is implemented with an end-to-end trained automatic spee…
View article: Personalized Keyphrase Detection using Speaker and Environment\n Information
Personalized Keyphrase Detection using Speaker and Environment\n Information Open
In this paper, we introduce a streaming keyphrase detection system that can\nbe easily customized to accurately detect any phrase composed of words from a\nlarge vocabulary. The system is implemented with an end-to-end trained\nautomatic s…
View article: Clone-structured graph representations enable flexible learning and vicarious evaluation of cognitive maps
Clone-structured graph representations enable flexible learning and vicarious evaluation of cognitive maps Open
Cognitive maps are mental representations of spatial and conceptual relationships in an environment, and are critical for flexible behavior. To form these abstract maps, the hippocampus has to learn to separate or merge aliased observation…
View article: Astrocyte glutamate uptake coordinates experience‐dependent, eye‐specific refinement in developing visual cortex
Astrocyte glutamate uptake coordinates experience‐dependent, eye‐specific refinement in developing visual cortex Open
The uptake of glutamate by astrocytes actively shapes synaptic transmission, however its role in the development and plasticity of neuronal circuits remains poorly understood. The astrocytic glutamate transporter, GLT1 is the predominant s…
View article: Learning attention-controllable border-ownership for objectness inference and binding
Learning attention-controllable border-ownership for objectness inference and binding Open
Human visual systems can parse a scene composed of novel objects and infer their surfaces and occlusion relationships without relying on object-specific shapes or textures. Perceptual grouping can bind together spatially disjoint entities …
View article: Astrocytic glutamate uptake coordinates experience-dependent, eye-specific refinement in developing visual cortex
Astrocytic glutamate uptake coordinates experience-dependent, eye-specific refinement in developing visual cortex Open
The uptake of glutamate by astrocytes actively shapes synaptic transmission, however its role in the development and plasticity of neuronal circuits remains poorly understood. The astrocytic glutamate transporter, GLT1 is the predominant s…
View article: Memorize-Generalize: An online algorithm for learning higher-order sequential structure with cloned Hidden Markov Models
Memorize-Generalize: An online algorithm for learning higher-order sequential structure with cloned Hidden Markov Models Open
Sequence learning is a vital cognitive function and has been observed in numerous brain areas. Discovering the algorithms underlying sequence learning has been a major endeavour in both neuroscience and machine learning. In earlier work we…
View article: Different clones for different contexts: Hippocampal cognitive maps as higher-order graphs of a cloned HMM
Different clones for different contexts: Hippocampal cognitive maps as higher-order graphs of a cloned HMM Open
Hippocampus encodes cognitive maps that support episodic memories, navigation, and planning. Under-standing the commonality among those maps as well as how those maps are structured, learned from experience, and used for inference and plan…
Prefrontal Computation as Active Inference Open
View article: Memorize-Generalize: An online algorithm for learning higher-order sequential structure with cloned Hidden Markov Models
Memorize-Generalize: An online algorithm for learning higher-order sequential structure with cloned Hidden Markov Models Open
Sequence learning is a vital cognitive function and has been observed in numerous brain areas. Discovering the algorithms underlying sequence learning has been a major endeavour in both neuroscience and machine learning. In earlier work we…
View article: Different clones for different contexts: Hippocampal cognitive maps as higher-order graphs of a cloned HMM
Different clones for different contexts: Hippocampal cognitive maps as higher-order graphs of a cloned HMM Open
View article: Thalamic regulation of switching between cortical representations enables cognitive flexibility
Thalamic regulation of switching between cortical representations enables cognitive flexibility Open
View article: Thalamic regulation of switching between cortical representations enables cognitive flexibility
Thalamic regulation of switching between cortical representations enables cognitive flexibility Open
View article: Reliable sensory processing in mouse visual cortex through inhibitory interactions between Somatostatin and Parvalbumin interneurons
Reliable sensory processing in mouse visual cortex through inhibitory interactions between Somatostatin and Parvalbumin interneurons Open
Cortical neurons often respond to identical sensory stimuli with large variability. However, under certain conditions, the same neurons can also respond highly reliably. The circuit mechanisms that contribute to this modulation, and their …
View article: Jointly reduced inhibition and excitation underlies circuit-wide changes in cortical processing in Rett syndrome
Jointly reduced inhibition and excitation underlies circuit-wide changes in cortical processing in Rett syndrome Open
Significance Understanding neurophysiological correlates of neurodevelopmental disorders is one of the pressing challenges of neuroscience. By analyzing a mouse model of Rett syndrome (RTT), we show that cortical pyramidal neurons in methy…
View article: Spatial Correlations in Natural Scenes Modulate Response Reliability in Mouse Visual Cortex
Spatial Correlations in Natural Scenes Modulate Response Reliability in Mouse Visual Cortex Open
Intrinsic neuronal variability significantly limits information encoding in the primary visual cortex (V1). Certain stimuli can suppress this intertrial variability to increase the reliability of neuronal responses. In particular, response…