Sort by
Refine Your Search
-
Listed
-
Category
-
Country
- United States
- France
- Germany
- United Kingdom
- Portugal
- Sweden
- Norway
- Spain
- Netherlands
- Belgium
- Japan
- Hong Kong
- Italy
- Luxembourg
- Poland
- Switzerland
- United Arab Emirates
- Denmark
- Brazil
- Ireland
- Singapore
- Finland
- Lithuania
- Saudi Arabia
- Vietnam
- Austria
- Canada
- Cyprus
- Czech
- Europe
- Malta
- Worldwide
- 22 more »
- « less
-
Program
-
Field
-
The postdoctoral researcher will join the "Network Dynamics & Computations" team led by Srdjan Ostojic and develop research projects on modeling neural circuits and their role in behavior. The work will focus
-
-aware AI under practical deployment constraints. Familiarity with efficient neural network architectures, including alternative attention mechanisms or mixture-of-experts models. Exposure to trustworthy
-
; 2.) use invasive and non-invasive brain stimulation to probe the causal relationship between neural network dynamics and behaviour; 3) leverage these insights to pioneer closed-loop approaches
-
; use invasive and non-invasive brain stimulation to probe the causal relationship between neural network dynamics and behaviour; leverage these insights to pioneer closed-loop approaches to therapeutic
-
Inria, the French national research institute for the digital sciences | Montbonnot Saint Martin, Rhone Alpes | France | about 23 hours ago
to reconstruct open rose flowers in 3D. The key idea is to learn two neural networks that operate on different scales. The first network operates on the scale of the full flower to identify the flower architecture
-
2026 Interviews: TBC (online) Start date: September 2026 Project Title: AI-Enhanced Battery State of Health Estimation Using Ring Probabilistic Logic Neural Networks Director of Studies: Prof Shahab
-
optimization. At the same time, AI models, especially deep neural networks, are becoming increasingly complex, with energy consumption and carbon footprint emerging as major concerns. For instance, training a
-
. Indeed, the methods currently used rely on optical image databases of various avalanche observations. A deep neural network was trained on this data to enable automatic avalanche detection FIGURE 1 (a) [1
-
implement and train neural network architectures, including Physics-Informed Neural Networks (PINNs), in order to integrate physical constraints into the learning process and improve the identification and
-
) relationship with the low-fidelity response. Extensions include nonlinear information fusion with GPs, Bayesian multi-fidelity inference and deep probabilistic surrogates, as well as MF neural networks