This is a hobby project that explores how the intelligence of a neural network (i.e. a primitive brain) might be optimized (i.e. evolved) across generations without using back propagation and real-time feedback.
Detailed description can be found in this webpage: The Little Fish
>>> git clone https://github.com/zhuangjun1981/littlefish
>>> cd littlefish
>>> pip install .
- first edit the
<repo directory>/littlefish/scripts/for_simulation/run_simulation_1.py- modify
data_folderto be a directory for saving simulation logs (can be several Gigs) - if running from scratch, make sure
start_generation_ind = 0
- modify
- Then run the script in python:
python <repo directory>/littlefish/scripts/for_simulation/run_simulation_1.py
- First start simulation viewer:
python <repo directory>/littlefish/viewer/simulation_viewer.py
- Click the
Choose Filebutton - Pick any
.hdf5file saved in the simulation log folder.

