Research

I’m generally interested in building capable and useful machine learning models using generic (requiring minimal domain knowledge or inductive biases) and scalable (data-efficient and compute-efficient) methods.

Papers

Orhan AE (2024) HVM-1: Large-scale video models pretrained with nearly 5000 hours of human-like video data.

Orhan AE, Wang W, Wang AN, Ren M, Lake BM (2024) Self-supervised learning of video representations from a child’s perspective.

Vong WK, Wang W, Orhan AE, Lake BM (2024) Grounded language acquisition through the eyes and ears of a single child. [pdf] [supp]

Orhan AE, Lake BM (2024) Learning high-level visual representations from a child’s perspective without strong inductive biases. [preprint]

Davidson G, Orhan AE, Lake BM (2024) Spatial relation categorization in infants and deep neural networks. [preprint]

Orhan AE (2023) Scaling may be all you need for achieving human-level object recognition capacity with human-like visual experience.

Orhan AE (2023) Recognition, recall, and retention of few-shot memories in large language models.

Orhan AE (2022) Can deep learning match the efficiency of human visual long-term memory in storing object details?

Orhan AE (2021) How much human-like visual experience do current SSL algorithms need to achieve human-level object recognition?

Orhan AE (2021) Compositional generalization in semantic parsing with pretrained transformers.

Yoon K, Orhan AE, Kim J, Pitkow X (2021) Two-argument activation functions learn soft XOR operations like cortical neurons.

Orhan AE, Gupta VV, Lake BM (2020) Self-supervised learning through the eyes of a child. [Press 1] [Press 2] [3-minute summary] [1-hour talk]

Orhan AE, Pitkow X (2020) Improved memory in recurrent neural networks with sequential non-normal dynamics. [5-minute summary]

Orhan AE (2019) Robustness properties of Facebook’s ResNeXt WSL models.

Orhan AE, Lake BM (2019) Improving the robustness of ImageNet classifiers using elements of human visual cognition.

Orhan AE, Ma WJ (2019) A diverse range of factors affect the nature of neural representations underlying short-term memory.

Orhan AE, Pitkow X (2018) Degeneracy, trainability, and generalization in deep neural networks.

Orhan AE (2018) A simple cache model for image recognition.

Orhan AE, Pitkow X (2018) Skip connections eliminate singularities.

Orhan AE, Ma WJ (2017) Efficient probabilistic inference in generic neural networks trained with non-probabilistic feedback.

Orhan AE, Ma WJ (2015) Neural population coding of multiple stimuli.

Orhan AE, Jacobs RA (2014) Are performance limitations in visual short-term memory tasks due to capacity limitations or model mismatch?

Orhan AE, Jacobs RA (2014) Toward ecologically realistic theories in visual short-term memory research.

Orhan* AE, Sims* CR, Jacobs RA, Knill DC (2014) The adaptive nature of visual working memory.

Orhan AE, Jacobs RA (2013) A probabilistic clustering theory of the organization of visual short-term memory.

Orhan AE, Jacobs RA (2011) Probabilistic modeling of dependencies among visual short-term memory representations.

Orhan AE, Michel MM, Jacobs RA (2010) Visual learning with reliable and unreliable features.

Emin Orhan