|
|
| Line 1: |
Line 1: |
| - | = '''Gradual Learning in Super Neural Networks''' =
| |
| - | === Research question ===
| |
| - | Can the modularity of the SNN help show what level of transferability it is between modules used in the different tasks in the curriculum?
| |
| | | | |
| - | === Hypothesis ===
| |
| - | By testing what modules are used in which optimal paths, this study might show a reuse of some modules in multiple tasks, which would indicate the value of curriculum design.
| |
| - | A high level of reuse might even point towards the possibility of one-shot learning in a saturated SNN
| |
| - |
| |
| - | === Suggested Experiment ===
| |
| - | Training an RL agent on some simple toy-environment like the LunarLander from OpenAI gym.
| |
| - | This requires some rework of the reward signal from the environment to fake rewards for subtasks in the curriculum.
| |
| - | Rewards in early subtasks might be clear-cut values (1 if reached sub-goal, 0 if fail)
| |
| - | : Read up on curriculum design techniques
| |
| - |
| |
| - |
| |
| - | = '''Capacity Increase''' =
| |
| - | === Research question ===
| |
| - | Can we estimate the decline in needed capacity for each new sub-task learned from the curriculum?
| |
| - | How "much" capacity is needed to learn a new meme?
| |
| - |
| |
| - | === Hypothesis ===
| |
| - | Previous studies show a decline in needed capacity for each new sub-task (cite: Progressive Neural Networks-paper).
| |
| - | If a metric can be defined for measuring the capacity change, we expect the results to confirm this.
| |
| - |
| |
| - |
| |
| - |
| |
| - | = '''Search for the first path?''' =
| |
| - | === Research question ===
| |
| - | Is there anything to gain from performing a proper search for the first path versus just picking a random path and training the weights?
| |
| - |
| |
| - | === Hypothesis ===
| |
| - | I think performance will have the same asymptote, but it will be reached in fewer training iterations. The only thing that might be
| |
| - | influenced by this path selection is that the modules in PathNet might have more interconnected dependencies. Maybe the layers are more
| |
| - | "independent" when the weights are updated as part of multiple paths? This might be important for transferability when learning future tasks.
| |
| - |
| |
| - | === Suggested experiment ===
| |
| - | Performing multiple small multi-task learning scenarios. Two tasks should be enough, but it is necessary to show that modules are reused in each scenario.
| |
| - | Test both picking a path and the full-on search for a path and compare convergence time for the second task.
| |
| - |
| |
| - | === Implemented experiment ===
| |
| - | * Information about the execution of the experiment
| |
| - |
| |
| - | === Results ===
| |
| - | * Plots and table contents showing experiment results
| |
| - |
| |
| - | === Conclusion ===
| |
| - | * What does the results tell me
| |
| - |
| |
| - |
| |
| - |
| |
| - |
| |
| - |
| |
| - | <!--
| |
| - | = Format =
| |
| - | === Research question ===
| |
| - | * What do I want to test/know/research?
| |
| - |
| |
| - | === Hypothesis ===
| |
| - | * What do I think my results will be and why?
| |
| - |
| |
| - | === Suggested experiment ===
| |
| - | * How is the experiment to be performed?
| |
| - | * What metrics are going to be used?
| |
| - |
| |
| - | === Implemented experiment ===
| |
| - | * Information about the execution of the experiment
| |
| - |
| |
| - | === Results ===
| |
| - | * Plots and table contents showing experiment results
| |
| - |
| |
| - | === Conclusion ===
| |
| - | * What does the results tell me
| |
| - | -->
| |
