Lab
Esther Mondragón's Lab
Institution: City, University of London
Department: Department of Computer Science
Featured research (6)
The research presented in this paper advances the integration of Hebbian learning into Convolutional Neural Networks (CNNs) for image processing, systematically exploring different architectures to build an optimal configuration, adhering to biological tenability. Hebbian learning operates on local unsupervised neural information to form feature representations, providing an alternative to the popular but arguably biologically implausible and computationally intensive backpropagation learning algorithm. The suggested optimal architecture significantly enhances recent research aimed at integrating Hebbian learning with competition mechanisms and CNNs, expanding their representational capabilities by incorporating hard Winner-Takes-All (WTA) competition, Gaussian lateral inhibition mechanisms and Bienenstock-Cooper-Munro (BCM) learning rule in a single model. The resulting model achieved 76% classification accuracy on CIFAR-10, rivalling its end-to-end backpropagation variant (77%) and critically surpassing the state-of-the-art hard-WTA performance in CNNs of the same network depth (64.6%) by 11.4%. Moreover, results showed clear indications of sparse hierarchical learning through increasingly complex and abstract receptive fields. In summary, our implementation enhances both the performance and the generalisability of the learnt representations and constitutes a crucial step towards more biologically realistic artificial neural networks
Inspired by cognitive theories of creativity, this paper introduces a computational model (AIGenC) that lays down the necessary components to enable artificial agents to learn, use and generate transferable representations. Unlike machine representations, which rely exclusively on raw sensory data, biological representations incorporate relational and associative information that embed a rich and structured concept space. The AIGenC model poses a hierarchical graph architecture with various levels and types of representations procured by the different components. The first component, Concept Processing, extracts objects and affordances from sensory input and encodes them into a concept space. The resulting representations are stored in a dual memory system and enriched with goal-directed and temporal information acquired through reinforcement learning, creating a higher-level of abstraction. Two additional and complementary components work in parallel to detect and recover relevant concepts through a matching process and create new ones, respectively, in a process akin to cognitive Reflective Reasoning and Blending. If Reflective Reasoning fails to offer a suitable solution, a blending operation creates new concepts by combining past information. We discuss the model’s capability to yield better out-of-distribution generalisation in artificial agents, thus advancing toward Artificial General Intelligence.
This paper introduces a computational model of creative problem-solving in deep reinforcement learning agents, inspired by cognitive theories of creativity. The AIGenC model aims at enabling artificial agents to learn, use and generate transferable representations. AIGenC is embedded in a deep learning architecture that includes three main components: concept processing, reflective reasoning, and blending of concepts. The first component extracts objects and affordances from sensory input and encodes them in a concept space, represented as a hierarchical graph structure. Concept representations are stored in a dual memory system. Goal-directed and temporal information acquired by the agent during deep reinforcement learning enriches the representations creating a higher level of abstraction in the concept space. In parallel, a process akin to reflective reasoning detects and recovers from memory concepts relevant to the task according to a matching process that calculates a similarity value between the current state and memory graph structures. Once an interaction is finalised, rewards and temporal information are added to the graph structure, creating a higher abstraction level. If reflective reasoning fails to offer a suitable solution, a blending process comes into place to create new concepts by combining past information. We discuss the model’s capability to yield better out-of-distribution generalisation in artificial agents, thus advancing toward artificial general intelligence. To the best of our knowledge, this is the first computational model, beyond mere formal theories, that posits a solution to creative problem solving within a deep learning architecture.
Lab head

Department
- Department of Computer Science
About Esther Mondragón
- I am a member of the Artificial Intelligence Research Centre (CitAI) and the Director of the MSc in Artificial Intelligence at City, University of London. As a computational cognitive neuroscientist, I work primarily in nature-inspired AI; to be more precise, I’m interested in integrating deep learning architectures and associative learning to model the process of learning stimulus representations