Search Results for author:
Found 19 papers, 6 papers with code
Large Language Model (LLM) as a System of Multiple Expert Agents: An Approach to solve the Abstraction and Reasoning Corpus (ARC) Challenge
We attempt to solve the Abstraction and Reasoning Corpus (ARC) Challenge using Large Language Models (LLMs) as a system of multiple expert agents.
Local Intrinsic Dimensional Entropy
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 $|\mathcal{X}|=\infty$).
Learning, Fast and Slow: A Goal-Directed Memory-Based Approach for Dynamic Environments
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).
AP: Selective Activation for De-sparsifying Pruned Neural Networks
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.
Optimizing Learning Rate Schedules for Iterative Pruning of Deep Neural Networks
(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.
Improving Mutual Information based Feature Selection by Boosting Unique Relevance
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.
Towards Better Long-range Time Series Forecasting using Generative Forecasting
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.
DropNet: Reducing Neural Network Complexity via Iterative Pruning
Modern deep neural networks require a significant amount of computing time and power to train and deploy, which limits their usage on edge devices.
Brick Tic-Tac-Toe: Exploring the Generalizability of AlphaZero to Novel Test Environments
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.
Achieving Low Complexity Neural Decoders via Iterative Pruning
The advancement of deep learning has led to the development of neural decoders for low latency communications.
Network-to-Network Regularization: Enforcing Occam's Razor to Improve Generalization
Empirical studies find that conventional training of neural networks, unlike network-to-network regularization, leads to networks of high KG and lower test accuracies.
S-Cyc: A Learning Rate Schedule for Iterative Pruning of ReLU-based Networks
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.
Towards Better Long-range Time Series Forecasting using Generative Adversarial Networks
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.
Using Synthetic Data to Improve the Long-range Forecasting of Time Series Data
Lastly, we conduct an ablation study to demonstrate the effectiveness of the cWGAN-GEP and the ITC algorithm.
Co-complexity: An Extended Perspective on Generalization Error
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.
Long-range Prediction of Vital Signs Using Generative Boosting via LSTM Networks
Vital signs including heart rate, respiratory rate, body temperature and blood pressure, are critical in the clinical decision making process.
Investigating Convolutional Neural Networks using Spatial Orderness
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).
Feature Selection Based on Unique Relevant Information for Health Data
Feature selection, which searches for the most representative features in observed data, is critical for health data analysis.
Second-Order Asymptotically Optimal Statistical Classification
Motivated by real-world machine learning applications, we analyze approximations to the non-asymptotic fundamental limits of statistical classification.
