Mandana Samiei

NeuMoSync: End-to-End Neuromodulatory Control for Plasticity and Adaptability in Continual Learning

Seyed Roozbeh Razavi Rohani, Khashayar Khajavi, Wesley Chung, Mandana Samiei et autres

Continual learning (CL) requires models to learn tasks sequentially, yet deep neural networks often suffer from plasticity loss and poor knowledge transfer, which can impede their long-term adaptability. Drawing high-level inspiration from global neuromodulatory mechanisms in the brain, we introduce Neuromodulation and …

NeuMoSync: End-to-End Neuromodulatory Control for Plasticity and Adaptability in Continual Learning

Seyed Roozbeh Razavi Rohani, Khashayar Khajavi, Wesley Chung, Mandana Samiei et autres

Continual learning (CL) requires models to learn tasks sequentially, yet deep neural networks often suffer from plasticity loss and poor knowledge transfer, which can impede their long-term adaptability. Drawing high-level inspiration from global neuromodulatory mechanisms in the brain, we introduce Neuromodulation and …

To Retain or to Adapt? Generalizing Continual Learning

Giulia Lanzillotta, Mandana Samiei, Doina Precup, Razvan Pascanu et autres

The Continual Learning (CL) literature has long been driven by the goal of mitigating catastrophic forgetting. This objective rests on a pervasive, often unstated assumption: that a lifelong learner should approximate the Joint-Task Learning (JTL) solution and retain all previously acquired knowledge. …

To Retain or to Adapt? Generalizing Continual Learning

Giulia Lanzillotta, Mandana Samiei, Doina Precup, Razvan Pascanu et autres

The Continual Learning (CL) literature has long been driven by the goal of mitigating catastrophic forgetting. This objective rests on a pervasive, often unstated assumption: that a lifelong learner should approximate the Joint-Task Learning (JTL) solution and retain all previously acquired knowledge. …

Human Adults and LLMs as Scientists: Who Benefits from Active Exploration?

Mandana Samiei, Eunice Yiu, Anthony GX-Chen, Dexin Lin et autres

A long-standing finding in the causal learning literature is that adults struggle to identify conjunctive causal rules, where an effect requires the simultaneous presence of multiple causes, while performing better in disjunctive settings. However, most demonstrations of this ``conjunctive handicap'' rely on …

Human Adults and LLMs as Scientists: Who Benefits from Active Exploration?

Mandana Samiei, Eunice Yiu, Anthony GX-Chen, Dexin Lin et autres

A long-standing finding in the causal learning literature is that adults struggle to identify conjunctive causal rules, where an effect requires the simultaneous presence of multiple causes, while performing better in disjunctive settings. However, most demonstrations of this ``conjunctive handicap'' rely on …

us, ca (code pays fourni par la source)

The schema spectrum: Emergent structures and levels of abstraction in AI and the brain

Mandana Samiei, Doina Precup, Blake A. Richards

ca (code pays fourni par la source)

Local Inconsistency Resolution: The Interplay between Attention and Control in Probabilistic Models

Oliver E. Richardson, Mandana Samiei, Mehran Shakerinava, Joseph D. Viviano et autres

We present a generic algorithm for learning and approximate inference with an intuitive epistemic interpretation: iteratively focus on a subset of the model and resolve inconsistencies using the parameters under control. This framework, which we call Local Inconsistency Resolution (LIR) is built …

Local Inconsistency Resolution: The Interplay between Attention and Control in Probabilistic Models

Oliver E. Richardson, Mandana Samiei, Mehran Shakerinava, Joseph D. Viviano et autres

We present a generic algorithm for learning and approximate inference with an intuitive epistemic interpretation: iteratively focus on a subset of the model and resolve inconsistencies using the parameters under control. This framework, which we call Local Inconsistency Resolution (LIR) is built …

ca, fr (code pays fourni par la source)

Possible Principles for Aligned Structure Learning Agents

Lancelot Da Costa, Tomáš Gavenčiak, David C. Hyland, Mandana Samiei et autres

This paper offers a road map for the development of scalable aligned artificial intelligence (AI) from first principle descriptions of natural intelligence. In brief, a possible path toward scalable aligned AI rests on enabling artificial agents to learn a good model of …

cz, gb, ca, au (code pays fourni par la source)

Possible Principles for Aligned Structure Learning Agents

Lancelot Da Costa, Tomáš Gavenčiak, David C. Hyland, Mandana Samiei et autres

This paper offers a roadmap for the development of scalable aligned artificial intelligence (AI) from first principle descriptions of natural intelligence. In brief, a possible path toward scalable aligned AI rests upon enabling artificial agents to learn a good model of the …

Convening during COVID-19: Lessons learnt from organizing virtual workshops in 2020

Mandana Samiei, Caroline V. Weis, Larissa Schiavo, Tatjana Chavdarova et autres

This report is an account of the authors' experiences as organizers of WiML's "Un-Workshop" event at ICML 2020. Un-workshops focus on participant-driven structured discussions on a pre-selected topic. For clarity, this event was different from the "WiML Workshop", which is usually co-located …