Search Results for author:
Found 19 papers, 4 papers with code
Predictive representations: building blocks of intelligence
Adaptive behavior often requires predicting future events.
Reconciling Shared versus Context-Specific Information in a Neural Network Model of Latent Causes
Through learning, it naturally stores structure that is shared across tasks in the network weights.
How should the advent of large language models affect the practice of science?
For this opinion piece, we have invited four diverse groups of scientists to reflect on this query, sharing their perspectives and engaging in debate.
Grokking as the Transition from Lazy to Rich Training Dynamics
We identify sufficient statistics for the test loss of such a network, and tracking these over training reveals that grokking arises in this setting when the network first attempts to fit a kernel regression solution with its initial features, followed by late-time feature learning where a generalizing solution is identified after train loss is already low.
Successor-Predecessor Intrinsic Exploration
Here we focus on exploration with intrinsic rewards, where the agent transiently augments the external rewards with self-generated intrinsic rewards.
The molecular memory code and synaptic plasticity: a synthesis
As an alternative, it has been proposed that molecules within the cell body are the storage sites of memory, and that memories are formed through biochemical operations on these molecules.
Representation learning with reward prediction errors
The Reward Prediction Error hypothesis proposes that phasic activity in the midbrain dopaminergic system reflects prediction errors needed for learning in reinforcement learning.
Human-Level Reinforcement Learning through Theory-Based Modeling, Exploration, and Planning
Here we propose a new approach to this challenge based on a particularly strong form of model-based RL which we call Theory-Based Reinforcement Learning, because it uses human-like intuitive theories -- rich, abstract, causal models of physical objects, intentional agents, and their interactions -- to explore and model an environment, and plan effectively to achieve task goals.
Hybrid Memoised Wake-Sleep: Approximate Inference at the Discrete-Continuous Interface
We build on a recent approach, Memoised Wake-Sleep (MWS), which alleviates part of the problem by memoising discrete variables, and extend it to allow for a principled and effective way to handle continuous variables by learning a separate recognition model used for importance-sampling based approximate inference and marginalization.
Language-Mediated, Object-Centric Representation Learning
These object-centric concepts derived from language facilitate the learning of object-centric representations.
Analyzing machine-learned representations: A natural language case study
Analyzing performance on these diagnostic tests indicates a lack of systematicity in the representations and decision rules, and reveals a set of heuristic strategies.
What does the free energy principle tell us about the brain?
The free energy principle has been proposed as a unifying account of brain function.
Human-in-the-Loop Interpretability Prior
We often desire our models to be interpretable as well as accurate.
Estimating scale-invariant future in continuous time
Widely used reinforcement learning algorithms discretize continuous time and estimate either transition functions from one step to the next (model-based algorithms) or a scalar value of exponentially-discounted future reward using the Bellman equation (model-free algorithms).
Evaluating Compositionality in Sentence Embeddings
Further, we find that augmenting training with our dataset improves test performance on our dataset without loss of performance on the original training dataset.
Probing the Compositionality of Intuitive Functions
How do people learn about complex functional structure?
Deep Successor Reinforcement Learning
The successor map represents the expected future state occupancy from any given state and the reward predictor maps states to scalar rewards.
Building Machines That Learn and Think Like People
Recent progress in artificial intelligence (AI) has renewed interest in building systems that learn and think like people.
Design Principles of the Hippocampal Cognitive Map
Furthermore, we demonstrate that this representation of space can support efficient reinforcement learning.
Hierarchical Reinforcement Learning
reinforcement-learning
+1
