User profiles for Arjun K Bansal
Arjun K BansalLog10 Verified email at log10.io Cited by 1202 |
Flexpoint: An adaptive numerical format for efficient training of deep neural networks
Deep neural networks are commonly developed and trained in 32-bit floating point format.
Significant gains in performance and energy efficiency could be realized by training and …
Significant gains in performance and energy efficiency could be realized by training and …
Decoding 3D reach and grasp from hybrid signals in motor and premotor cortices: spikes, multiunit activity, and local field potentials
AK Bansal, W Truccolo… - Journal of …, 2012 - journals.physiology.org
Neural activity in motor cortex during reach and grasp movements shows modulations in a
broad range of signals from single-neuron spiking activity (SA) to various frequency bands in …
broad range of signals from single-neuron spiking activity (SA) to various frequency bands in …
Discovering hidden factors of variation in deep networks
Deep learning has enjoyed a great deal of success because of its ability to learn useful
features for tasks such as classification. But there has been less exploration in learning the …
features for tasks such as classification. But there has been less exploration in learning the …
Intel ngraph: An intermediate representation, compiler, and executor for deep learning
The Deep Learning (DL) community sees many novel topologies published each year.
Achieving high performance on each new topology remains challenging, as each requires some …
Achieving high performance on each new topology remains challenging, as each requires some …
Relationships among low-frequency local field potentials, spiking activity, and three-dimensional reach and grasp kinematics in primary motor and ventral premotor …
AK Bansal, CE Vargas-Irwin… - Journal of …, 2011 - journals.physiology.org
A prominent feature of motor cortex field potentials during movement is a distinctive low-frequency
local field potential (lf-LFP) (<4 Hz), referred to as the movement event-related …
local field potential (lf-LFP) (<4 Hz), referred to as the movement event-related …
Deep semantic protein representation for annotation, discovery, and engineering
Computational assignment of function to proteins with no known homologs is still an unsolved
problem. We have created a novel, function-based approach to protein annotation and …
problem. We have created a novel, function-based approach to protein annotation and …
Hierarchical policy learning is sensitive to goal space design
Hierarchy in reinforcement learning agents allows for control at multiple time scales yielding
improved sample efficiency, the ability to deal with long time horizons and transferability of …
improved sample efficiency, the ability to deal with long time horizons and transferability of …
Neural dynamics underlying target detection in the human brain
Sensory signals must be interpreted in the context of goals and tasks. To detect a target in
an image, the brain compares input signals and goals to elicit the correct behavior. We …
an image, the brain compares input signals and goals to elicit the correct behavior. We …
Temporal stability of visually selective responses in intracranial field potentials recorded from human occipital and temporal lobes
The cerebral cortex needs to maintain information for long time periods while at the same
time being capable of learning and adapting to changes. The degree of stability of …
time being capable of learning and adapting to changes. The degree of stability of …
Neural interactions underlying Visuomotor associations in the human brain
Rapid and flexible learning during behavioral choices is critical to our daily endeavors and
constitutes a hallmark of dynamic reasoning. An important paradigm to examine flexible …
constitutes a hallmark of dynamic reasoning. An important paradigm to examine flexible …