Publications related to Neuroevolution

Combining biophysical models and machine learning to optimize implant geometry and stimulation protocol for intraneural electrodes

Silvestro Micera, Simone Romeni, Elena Losanno, Luca Pierantoni

Objective. Peripheral nerve interfaces have the potential to restore sensory, motor, and visceral functions. In particular, intraneural interfaces allow targeting deep neural structures with high selectivity, even if their performance strongly depends upon ...

IOP Publishing Ltd2023

Second-order guarantees in centralized, federated and decentralized nonconvex optimization

Ali H. Sayed, Stefan Vlaski

Rapid advances in data collection and processing capabilities have allowed for the use of increasingly complex models that give rise to nonconvex optimization problems. These formulations, however, can be arbitrarily difficult to solve in general, in the s ...

INT PRESS BOSTON, INC2020

Capsule networks, but not convolutional networks explain global configurational visual effects

Michael Herzog, Adrien Christophe Doerig, Alban Bornet

In human vision, perception of local features depends on all elements in the visual field and their exact configuration. For example, observers performed a vernier discrimination task. When a surrounding square was added to the vernier, the task became muc ...

2019

Error Feedback Fixes SignSGD and other Gradient Compression Schemes

Martin Jaggi, Sebastian Urban Stich, Quentin Rebjock, Sai Praneeth Reddy Karimireddy

Sign-based algorithms (e.g. signSGD) have been proposed as a biased gradient compression technique to alleviate the communication bottleneck in training large neural networks across multiple workers. We show simple convex counter-examples where signSGD doe ...

PMLR2019

Error Feedback Fixes SignSGD and other Gradient Compression Schemes

Martin Jaggi, Sebastian Urban Stich, Quentin Rebjock, Sai Praneeth Reddy Karimireddy

2019

IMPACT: Interval-based Multi-pass Proteomic Alignment with Constant Traceback

James Richard Larus, Sahand Kashani, Stuart Anthony Byma

Darwin is a genomics co-processor that achieved a 15000x acceleration on long read assembly through innovative hardware and algorithm co-design. Darwins algorithms and hardware implementation were specifically designed for DNA analysis pipelines. This pape ...

2019

Low-rank and Sparse Soft Targets to Learn Better DNN Acoustic Models

Hervé Bourlard, Afsaneh Asaei, Pranay Dighe

Conventional deep neural networks (DNN) for speech acoustic modeling rely on Gaussian mixture models (GMM) and hidden Markov model (HMM) to obtain binary class labels as the targets for DNN training. Subword classes in speech recognition systems correspond ...

Ieee2017

Gaining Insight into Quality Diversity

Dario Floreano, Joshua Evan Auerbach, Giovanni Iacca

Recently there has been a growing movement of researchers that believes innovation and novelty creation, rather than pure optimization, are the true strengths of evolutionary algorithms relative to other forms of machine learning. This idea also provides o ...

ACM Press2016

Memetic Viability Evolution for Constrained Optimization

Dario Floreano, Andrea Maesani, Giovanni Iacca

The performance of evolutionary algorithms can be heavily undermined when constraints limit the feasible areas of the search space. For instance, while Covariance Matrix Adapta- tion Evolution Strategy is one of the most efficient algorithms for unconstrai ...

Institute of Electrical and Electronics Engineers2016

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

Neuroevolution

Combining biophysical models and machine learning to optimize implant geometry and stimulation protocol for intraneural electrodes

Second-order guarantees in centralized, federated and decentralized nonconvex optimization

The Little W-Net That Could: State-of-the-Art Retinal Vessel Segmentation with Minimalistic Models

Capsule networks, but not convolutional networks explain global configurational visual effects

Error Feedback Fixes SignSGD and other Gradient Compression Schemes

Error Feedback Fixes SignSGD and other Gradient Compression Schemes

IMPACT: Interval-based Multi-pass Proteomic Alignment with Constant Traceback

Low-rank and Sparse Soft Targets to Learn Better DNN Acoustic Models

Gaining Insight into Quality Diversity

Memetic Viability Evolution for Constrained Optimization

Graph Chatbot

Chat with Graph Search

The Little W-Net That Could: State-of-the-Art Retinal Vessel Segmentation with Minimalistic Models

IMPACT: Interval-based Multi-pass Proteomic Alignment with Constant Traceback

Second-order guarantees in centralized, federated and decentralized nonconvex optimization

Error Feedback Fixes SignSGD and other Gradient Compression Schemes

Memetic Viability Evolution for Constrained Optimization

Combining biophysical models and machine learning to optimize implant geometry and stimulation protocol for intraneural electrodes

Error Feedback Fixes SignSGD and other Gradient Compression Schemes

Gaining Insight into Quality Diversity

Low-rank and Sparse Soft Targets to Learn Better DNN Acoustic Models

Capsule networks, but not convolutional networks explain global configurational visual effects