Sensorium: Visual Cortex Modeling
Computational Modeling
Neural Prediction
Vision Science
RNNs
Accurate predictive models of 28,000 neurons from primary visual cortex responses (captured using calcium imaging) to thousands of natural stimuli. Achieved a single trial correlation of 0.41 using an optimized HMAX model with neural circuits & recurrent connections. Placed 4th in the NeurIPS workshop competition.
Technologies Used: Python, PyTorch, Deep Learning.
My Role:
- Built multiple models using HMAX to predict neural data from the mouse visual cortex to natural images.
- Worked on a scientifically accurate visual model for the mouse brain with feedback connections.