Alert button
Picture for Beomseok Kang

Beomseok Kang

Alert button

Unsupervised 3D Object Learning through Neuron Activity aware Plasticity

Feb 22, 2023
Beomseok Kang, Biswadeep Chakraborty, Saibal Mukhopadhyay

Figure 1 for Unsupervised 3D Object Learning through Neuron Activity aware Plasticity
Figure 2 for Unsupervised 3D Object Learning through Neuron Activity aware Plasticity
Figure 3 for Unsupervised 3D Object Learning through Neuron Activity aware Plasticity
Figure 4 for Unsupervised 3D Object Learning through Neuron Activity aware Plasticity

We present an unsupervised deep learning model for 3D object classification. Conventional Hebbian learning, a well-known unsupervised model, suffers from loss of local features leading to reduced performance for tasks with complex geometric objects. We present a deep network with a novel Neuron Activity Aware (NeAW) Hebbian learning rule that dynamically switches the neurons to be governed by Hebbian learning or anti-Hebbian learning, depending on its activity. We analytically show that NeAW Hebbian learning relieves the bias in neuron activity, allowing more neurons to attend to the representation of the 3D objects. Empirical results show that the NeAW Hebbian learning outperforms other variants of Hebbian learning and shows higher accuracy over fully supervised models when training data is limited.

* Published as a conference paper at ICLR 2023 
Viaarxiv icon

Forecasting local behavior of multi-agent system and its application to forest fire model

Oct 28, 2022
Beomseok Kang, Minah Lee, Harshit Kumar, Saibal Mukhopadhyay

Figure 1 for Forecasting local behavior of multi-agent system and its application to forest fire model
Figure 2 for Forecasting local behavior of multi-agent system and its application to forest fire model
Figure 3 for Forecasting local behavior of multi-agent system and its application to forest fire model
Figure 4 for Forecasting local behavior of multi-agent system and its application to forest fire model

In this paper, we study a CNN-LSTM model to forecast the state of a specific agent in a large multi-agent system. The proposed model consists of a CNN encoder to represent the system into a low-dimensional vector, a LSTM module to learn the agent dynamics in the vector space, and a MLP decoder to predict the future state of an agent. A forest fire model is considered as an example where we need to predict when a specific tree agent will be burning. We observe that the proposed model achieves higher AUC with less computation than a frame-based model and significantly saves computational costs such as the activation than ConvLSTM.

* submitted to IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 
Viaarxiv icon