• Publications
  • Influence
Review of stability properties of neural plasticity rules for implementation on memristive neuromorphic hardware
TLDR
In the foreseeable future, synergistic advances in high-density memristive memory, scalable and massively parallel hardware, and neural network research will enable modelers to design large-scale, adaptive neural systems to support complex behaviors in virtual and robotic agents. Expand
  • 13
  • 3
  • PDF
The brain of a new machine
TLDR
MoNETA (Modular Neural Exploring Traveling Agent) is the software we're designing at Boston University's department of cognitive and neural systems, which will run on a braininspired microprocessor under development at HP Labs. Expand
  • 86
  • 2
Joining distributed pattern processing and homeostatic plasticity in recurrent on-center off-surround shunting networks: Noise, saturation, short-term memory, synaptic scaling, and BDNF
TLDR
The activities of neurons vary within small intervals that are bounded both above and below, yet the inputs to these neurons may vary many-fold. Expand
  • 15
  • 2
  • PDF
IPv4 Reassembly Errors at High Data Rates
TLDR
IPv4 fragmentation is not sufficiently robust for use under some conditions in today's Internet. Expand
  • 21
  • 1
From Synapses to Circuitry: Using Memristive Memory to Explore the Electronic Brain
TLDR
In a synchronous digital platform for building large cognitive models, memristive nanodevices form dense, resistive memories that can be placed close to conventional processing circuitry. Expand
  • 94
  • PDF
Mitigation of Effects of Occlusion on Object Recognition with Deep Neural Networks through Low-Level Image Completion
TLDR
We introduce a novel method for mitigating the difficulty of classification through dataset augmentation via inpainting, which in turn relies on the ability to segment object pixels from background. Expand
  • 8
  • PDF
General form of learning algorithms for neuromorphic hardware implementation
TLDR
The DARPA Systems of Neuromorphic Adaptive Plastic Scalable Electronics (SyNAPSE) initiative aims to create a new generation of high-density, low-power consumption chips capable of replicating adaptive and intelligent behavior observed in animals. Expand
  • 5
Review and unification of learning framework in Cog Ex Machina platform for memristive neuromorphic hardware
TLDR
This paper characterizes a subset of local learning rules amenable to implementation in memristive hardware. Expand
  • 9
Learning in a Distributed Software Architecture for Large-Scale Neural Modeling
TLDR
We focus on constraints related to learning in a simple visual system and those imposed by a new neural simulator for heterogeneous hardware systems, CogExMachina (Cog). Expand