Browsing by Author "Kozat, Serdar"
Now showing 1 - 2 of 2
Results Per Page
Sort Options
Item Open Access Online training of LSTM networks in distributed systems for variable length data sequences(Institute of Electrical and Electronics Engineers, 2018) Ergen, T.; Kozat, SerdarIn this brief, we investigate online training of long short term memory (LSTM) architectures in a distributed network of nodes, where each node employs an LSTM-based structure for online regression. In particular, each node sequentially receives a variable length data sequence with its label and can only exchange information with its neighbors to train the LSTM architecture. We first provide a generic LSTM-based regression structure for each node. In order to train this structure, we put the LSTM equations in a nonlinear state-space form for each node and then introduce a highly effective and efficient distributed particle filtering (DPF)-based training algorithm. We also introduce a distributed extended Kalman filtering-based training algorithm for comparison. Here, our DPF-based training algorithm guarantees convergence to the performance of the optimal LSTM coefficients in the mean square error sense under certain conditions. We achieve this performance with communication and computational complexity in the order of the first-order gradient-based methods. Through both simulated and real-life examples, we illustrate significant performance improvements with respect to the state-of-The-Art methods.Item Open Access User feedback-based online learning for intent classification(Association for Computing Machinery, 2023-10-09) Gönç, Kaan; Sağlam, Baturay; Dalmaz, Onat; Çukur, Tolga; Kozat, Serdar; Dibeklioğlu, HamdiIntent classifcation is a key task in natural language processing (NLP) that aims to infer the goal or intention behind a user’s query. Most existing intent classifcation methods rely on supervised deep models trained on large annotated datasets of text-intent pairs. However, obtaining such datasets is often expensive and impractical in real-world settings. Furthermore, supervised models may overft or face distributional shifts when new intents, utterances, or data distributions emerge over time, requiring frequent retraining. Online learning methods based on user feedback can overcome this limitation, as they do not need access to intents while collecting data and adapting the model continuously. In this paper, we propose a novel multi-armed contextual bandit framework that leverages a text encoder based on a large language model (LLM) to extract the latent features of a given utterance and jointly learn multimodal representations of encoded text features and intents. Our framework consists of two stages: ofine pretraining and online fne-tuning. In the ofine stage, we train the policy on a small labeled dataset using a contextual bandit approach. In the online stage, we fne-tune the policy parameters using the REINFORCE algorithm with a user feedback-based objective, without relying on the true intents. We further introduce a sliding window strategy for simulating the retrieval of data samples during online training. This novel two-phase approach enables our method to efciently adapt to dynamic user preferences and data distributions with improved performance. An extensive set of empirical studies indicate that our method signifcantly outperforms policies that omit either offine pretraining or online fne-tuning, while achieving competitive performance to a supervised benchmark trained on an order of magnitude larger labeled dataset.