1 code implementation • 8 Oct 2023 • John Chong Min Tan, Mehul Motani
We attempt to solve the Abstraction and Reasoning Corpus (ARC) Challenge using Large Language Models (LLMs) as a system of multiple expert agents.
1 code implementation • 5 Apr 2023 • Rohan Ghosh, Mehul Motani
For a finite $|\mathcal{X}|$, this yields robust entropy measures which satisfy many important properties, such as invariance to bijections, while the same is not true for continuous spaces (where $|\mathcal{X}|=\infty$).
1 code implementation • 31 Jan 2023 • John Chong Min Tan, Mehul Motani
To address these challenges, we do the following: i) Instead of a neural network, we do model-based planning using a parallel memory retrieval system (which we term the slow mechanism); ii) Instead of learning state values, we guide the agent's actions using goal-directed exploration, by using a neural network to choose the next action given the current state and the goal state (which we term the fast mechanism).
no code implementations • 9 Dec 2022 • Shiyu Liu, Rohan Ghosh, Dylan Tan, Mehul Motani
However, in network pruning, we find that the sparsity introduced by ReLU, which we quantify by a term called dynamic dead neuron rate (DNR), is not beneficial for the pruned network.
no code implementations • 9 Dec 2022 • Shiyu Liu, Rohan Ghosh, John Tan Chong Min, Mehul Motani
(ii) In addition to the strong theoretical motivation, SILO is empirically optimal in the sense of matching an Oracle, which exhaustively searches for the optimal value of max_lr via grid search.
no code implementations • 9 Dec 2022 • Shiyu Liu, Mehul Motani
MRwMR-BUR-CLF further improves the classification performance by 3. 8%- 5. 5% (relative to MRwMR), and it also outperforms three popular classifier dependent feature selection methods.
no code implementations • 9 Dec 2022 • Shiyu Liu, Rohan Ghosh, Mehul Motani
In this paper, we propose a new forecasting strategy called Generative Forecasting (GenF), which generates synthetic data for the next few time steps and then makes long-range forecasts based on generated and observed data.
1 code implementation • ICML 2020 • John Tan Chong Min, Mehul Motani
Modern deep neural networks require a significant amount of computing time and power to train and deploy, which limits their usage on edge devices.
1 code implementation • 13 Jul 2022 • John Tan Chong Min, Mehul Motani
Hence, current RL methods are largely not generalizable to a test environment which is conceptually similar but different from what the method has been trained on, which we term the novel test environment.
no code implementations • 11 Dec 2021 • Vikrant Malik, Rohan Ghosh, Mehul Motani
The advancement of deep learning has led to the development of neural decoders for low latency communications.
1 code implementation • NeurIPS 2021 • Rohan Ghosh, Mehul Motani
Empirical studies find that conventional training of neural networks, unlike network-to-network regularization, leads to networks of high KG and lower test accuracies.
no code implementations • 17 Oct 2021 • Shiyu Liu, Chong Min John Tan, Mehul Motani
We explore a new perspective on adapting the learning rate (LR) schedule to improve the performance of the ReLU-based network as it is iteratively pruned.
no code implementations • 17 Oct 2021 • Shiyu Liu, Rohan Ghosh, Mehul Motani
In this paper, we propose a new forecasting strategy called Generative Forecasting (GenF), which generates synthetic data for the next few time steps and then makes long-range forecasts based on generated and observed data.
no code implementations • 1 Jan 2021 • Shiyu Liu, Mehul Motani
Lastly, we conduct an ablation study to demonstrate the effectiveness of the cWGAN-GEP and the ITC algorithm.
no code implementations • 1 Jan 2021 • Rohan Ghosh, Mehul Motani
Subsequently, we propose a joint entropy-like measure of complexity between function spaces (classifier and generator), called co-complexity, which leads to tighter bounds on the generalization error in this setting.
no code implementations • 14 Nov 2019 • Shiyu Liu, Mehul Motani
Vital signs including heart rate, respiratory rate, body temperature and blood pressure, are critical in the clinical decision making process.
no code implementations • 18 Aug 2019 • Rohan Ghosh, Anupam K. Gupta, Mehul Motani
Convolutional Neural Networks (CNN) have been pivotal to the success of many state-of-the-art classification problems, in a wide variety of domains (for e. g. vision, speech, graphs and medical imaging).
no code implementations • 2 Dec 2018 • Shiyu Liu, Mehul Motani
Feature selection, which searches for the most representative features in observed data, is critical for health data analysis.
no code implementations • 3 Jun 2018 • Lin Zhou, Vincent Y. F. Tan, Mehul Motani
Motivated by real-world machine learning applications, we analyze approximations to the non-asymptotic fundamental limits of statistical classification.