no code implementations • 12 Apr 2024 • Lars Niedermeier, Jeffrey L. Krichmar
Spiking Neural Networks (SNNs) and neuromorphic models are more efficient and have more biological realism than the activation functions typically used in deep neural networks, transformer models and generative AI.
no code implementations • 18 May 2022 • Jinwei Xing, Takashi Nagata, Xinyun Zou, Emre Neftci, Jeffrey L. Krichmar
Although deep Reinforcement Learning (RL) has proven successful in a wide range of tasks, one challenge it faces is interpretability when applied to real-world problems.
no code implementations • 22 May 2021 • Jeffrey L. Krichmar
In 2006, during a meeting of a working group of scientists in La Jolla, California at The Neurosciences Institute (NSI), Gerald Edelman described a roadmap towards the creation of a Conscious Artifact.
no code implementations • 5 May 2021 • Shihao Song, Jui Hanamshet, Adarsha Balaji, Anup Das, Jeffrey L. Krichmar, Nikil D. Dutt, Nagarajan Kandasamy, Francky Catthoor
We propose a new architectural technique to mitigate the aging-related reliability problems in neuromorphic systems, by designing an intelligent run-time manager (NCRTM), which dynamically destresses neuron and synapse circuits in response to the short-term aging in their CMOS transistors during the execution of machine learning workloads, with the objective of meeting a reliability target.
no code implementations • 25 Feb 2021 • Xinyun Zou, Eric O. Scott, Alexander B. Johnson, Kexin Chen, Douglas A. Nitz, Kenneth A. De Jong, Jeffrey L. Krichmar
Animals ranging from rats to humans can demonstrate cognitive map capabilities.
1 code implementation • 10 Feb 2021 • Jinwei Xing, Takashi Nagata, Kexin Chen, Xinyun Zou, Emre Neftci, Jeffrey L. Krichmar
To address this issue, we propose a two-stage RL agent that first learns a latent unified state representation (LUSR) which is consistent across multiple domains in the first stage, and then do RL training in one source domain based on LUSR in the second stage.
1 code implementation • 21 Mar 2020 • Adarsha Balaji, Prathyusha Adiraju, Hirak J. Kashyap, Anup Das, Jeffrey L. Krichmar, Nikil D. Dutt, Francky Catthoor
We also use PyCARL to analyze these SNNs for a state-of-the-art neuromorphic hardware and demonstrate a significant performance deviation from software-only simulations.
1 code implementation • 21 Sep 2019 • Pawel Ladosz, Eseoghene Ben-Iwhiwhu, Jeffery Dick, Yang Hu, Nicholas Ketz, Soheil Kolouri, Jeffrey L. Krichmar, Praveen Pilly, Andrea Soltoggio
This paper presents a new neural architecture that combines a modulated Hebbian network (MOHN) with DQN, which we call modulated Hebbian plus Q network architecture (MOHQA).
no code implementations • 14 Sep 2019 • Jinwei Xing, Xinyun Zou, Jeffrey L. Krichmar
In the present paper, we take inspiration from the serotonergic system and apply it to the task of robot navigation.
no code implementations • 4 Sep 2019 • Adarsha Balaji, Anup Das, Yuefeng Wu, Khanh Huynh, Francesco Dell'Anna, Giacomo Indiveri, Jeffrey L. Krichmar, Nikil Dutt, Siebren Schaafsma, Francky Catthoor
SpiNePlacer then finds the best placement of local and global synapses on the hardware using a meta-heuristic-based approach to minimize energy consumption and spike latency.
1 code implementation • 9 Mar 2019 • Hirak J. Kashyap, Charless Fowlkes, Jeffrey L. Krichmar
Dynamic scenes that contain both object motion and egomotion are a challenge for monocular visual odometry (VO).
no code implementations • 16 Feb 2019 • Xinyun Zou, Soheil Kolouri, Praveen K. Pilly, Jeffrey L. Krichmar
In uncertain domains, the goals are often unknown and need to be predicted by the organism or system.
no code implementations • 4 Dec 2018 • Jeffrey L. Krichmar, William Severa, Salar M. Khan, James L. Olds
First, that scientific societies and governments coordinate Biomimetic Research for Energy-efficient, AI Designs (BREAD); a multinational initiative and a funding strategy for investments in the future integrated design of energetics into AI.
no code implementations • 18 Jul 2017 • Anup Das, Paruthi Pradhapan, Willemijn Groenendaal, Prathyusha Adiraju, Raj Thilak Rajan, Francky Catthoor, Siebren Schaafsma, Jeffrey L. Krichmar, Nikil Dutt, Chris Van Hoof
The novelty of our approach lies in (1) encoding spatio-temporal properties of ECG signals directly into spike train and using this to excite recurrently connected spiking neurons in a Liquid State Machine computation model; (2) a novel learning algorithm; and (3) an intelligently designed unsupervised readout based on Fuzzy c-Means clustering of spike responses from a subset of neurons (Liquid states), selected using particle swarm optimization.