no code implementations • 30 Jan 2024 • Kausik Lakkaraju, Vedant Khandelwal, Biplav Srivastava, Forest Agostinelli, Hengtao Tang, Prathamjeet Singh, Dezhi Wu, Matt Irvin, Ashish Kundu
Artificial intelligence (AI) has the potential to transform education with its power of uncovering insights from massive data about student learning patterns.
no code implementations • 25 Jul 2023 • Bharath Muppasani, Vishal Pallagani, Biplav Srivastava, Forest Agostinelli
The fastest solver today for RC is DeepCubeA with a custom representation, and another approach is with Scorpion planner with State-Action-Space+ (SAS+) representation.
no code implementations • 2 Jun 2023 • Hamed Damirchi, Forest Agostinelli, Pooyan Jamshidi
However, a lack of structure in each module's role, and modular network-specific issues such as module collapse have restricted their usability.
no code implementations • 8 Feb 2021 • Forest Agostinelli, Alexander Shmakov, Stephen Mcaleer, Roy Fox, Pierre Baldi
We use Q* search to solve the Rubik's cube when formulated with a large action space that includes 1872 meta-actions and find that this 157-fold increase in the size of the action space incurs less than a 4-fold increase in computation time and less than a 3-fold increase in number of nodes generated when performing Q* search.
no code implementations • 16 Jun 2020 • Mohammadamin Tavakoli, Forest Agostinelli, Pierre Baldi
Furthermore, we show that SPLASH units significantly increase the robustness of deep neural networks to adversarial attacks.
no code implementations • 25 Sep 2019 • Mohammadamin Tavakoli, Forest Agostinelli, Pierre Baldi
Finally, we show that the use of Symmetric-APL activations can significantly increase the robustness of deep neural networks to adversarial attacks.
no code implementations • ICLR 2019 • Stephen McAleer, Forest Agostinelli, Alexander Shmakov, Pierre Baldi
Autodidactic Iteration is able to learn how to solve the Rubik’s Cube and the 15-puzzle without relying on human data.
9 code implementations • 18 May 2018 • Stephen McAleer, Forest Agostinelli, Alexander Shmakov, Pierre Baldi
A generally intelligent agent must be able to teach itself how to solve problems in complex domains with minimal human supervision.
3 code implementations • 21 Dec 2014 • Forest Agostinelli, Matthew Hoffman, Peter Sadowski, Pierre Baldi
Artificial neural networks typically have a fixed, non-linear activation function at each neuron.
Ranked #162 on Image Classification on CIFAR-10
no code implementations • NeurIPS 2013 • Forest Agostinelli, Michael R. Anderson, Honglak Lee
Stacked sparse denoising auto-encoders (SSDAs) have recently been shown to be successful at removing noise from corrupted images.