From 6a11e214d47e5022e0631214e50990e1b794e3ab Mon Sep 17 00:00:00 2001 From: Amira Abdel-Rahman <amira-rahman@aucegypt.edu> Date: Thu, 16 Jul 2020 09:09:04 -0400 Subject: [PATCH] AI that grows --- 02_Presentation/AI_that_grows/AI_grow.md | 13 +++++++------ 02_Presentation/macro_dice/macro_dice.md | 15 +++++++-------- 2 files changed, 14 insertions(+), 14 deletions(-) diff --git a/02_Presentation/AI_that_grows/AI_grow.md b/02_Presentation/AI_that_grows/AI_grow.md index 06c0ca5..4d0be6d 100644 --- a/02_Presentation/AI_that_grows/AI_grow.md +++ b/02_Presentation/AI_that_grows/AI_grow.md @@ -8,10 +8,11 @@ Research and development of workflows for the co-design reconfigurable AI softwa - "focus on finding minimal architectures". - "By deemphasizing learning of weight parameters, we encourage the agent instead to develop ever-growing networks that can encode acquired skills based on its interactions with the environment". - - -<img src="./square_biped.png" width="50%" /><img src="./square_biped.gif" width="50%" /> +<img src="./WANN_schematic.png" width="70%" /> +<img src="./WANN_operators.png" width="70%" /> + +<img src="./square_biped.png" width="35%" /><img src="./square_biped.gif" width="35%" /> ## Case Study Implementation: Cart-Pole Swing Up @@ -21,7 +22,7 @@ One of the most famous benchmarks of non-linear control, there is lots of approa WANN is interesting as it tries to get the simplest network that uses the input sensors (position, rotation and their derivatives) to the output (force). It focuses on learning **principles** and **not only tune weights**. -<img src="./swing_best.png" width="100%" /> +<img src="./swing_best.png" width="75%" /> This is one of the outputs of the network and you can see because of it's simplicity it's not a black box and one can deduce the principles learnt [[1]](https://towardsdatascience.com/weight-agnostic-neural-networks-fce8120ee829): - the position parameter is almost directly linked to the force, there is only an inverter which means that if the cart is on right or left of the center (+- x), it always try to **go to in the opposite direction** to the center. @@ -30,9 +31,9 @@ This is one of the outputs of the network and you can see because of it's simpli ## Evolution and DICE Integration -<img src="./wann_run.png" width="100%" /> +<img src="./evol1.gif" width="50%" /> -<img src="./evol1.gif" width="75%" /> +<img src="./wann_run.png" width="50%" /> <img src="./quick.gif" width="100%" /> diff --git a/02_Presentation/macro_dice/macro_dice.md b/02_Presentation/macro_dice/macro_dice.md index e588fdc..910535d 100644 --- a/02_Presentation/macro_dice/macro_dice.md +++ b/02_Presentation/macro_dice/macro_dice.md @@ -12,23 +12,22 @@ Hardware Implementation: Using the [MetaVoxel simulation tool](https://gitlab.cba.mit.edu/amiraa/metavoxels): - +<img src="./200114_simulation.PNG" width="75%" /><br/> ## Robotics Design -<img src="./dice_assembly.gif" width="100%" /><br/> +<img src="./dice_assembly.gif" width="75%" /><br/> ## Assembly - Option for different kinds of assembly (swarm assembly) -<img src="./assembly.gif" width="100%" /> <br/> +<img src="./assembly.gif" width="75%" /> <br/> ## Control -<img src="./rover1.gif" width="75%" /> -<img src="./rover2.gif" width="75%" /><br/> +<img src="./rover1.gif" width="50%" /> +<img src="./rover2.gif" width="50%" /><br/> -<img src="./r.gif" width="75%" /><br/> - -<img src="./rr.gif" width="75%" /><br/> +<img src="./r.gif" width="50%" /><br/> +<img src="./rr.gif" width="50%" /><br/> ## Optimization -- GitLab