Zobrazeno 1 - 10
of 45
pro vyhledávání: '"Jati, Arindam"'
Autor:
Bhattacharya, Debarpan, Mukherjee, Sumanta, Kamanchi, Chandramouli, Ekambaram, Vijay, Jati, Arindam, Dayama, Pankaj
Time series anomaly detection (TSAD) is an evolving area of research motivated by its critical applications, such as detecting seismic activity, sensor failures in industrial plants, predicting crashes in the stock market, and so on. Across domains,
Externí odkaz:
http://arxiv.org/abs/2409.13053
Autor:
Kamanchi, Chandramouli, Mukherjee, Sumanta, Sampath, Kameshwaran, Dayama, Pankaj, Jati, Arindam, Ekambaram, Vijay, Phan, Dzung
Activation functions are non-linearities in neural networks that allow them to learn complex mapping between inputs and outputs. Typical choices for activation functions are ReLU, Tanh, Sigmoid etc., where the choice generally depends on the applicat
Externí odkaz:
http://arxiv.org/abs/2408.03599
Autor:
Ekambaram, Vijay, Jati, Arindam, Dayama, Pankaj, Mukherjee, Sumanta, Nguyen, Nam H., Gifford, Wesley M., Reddy, Chandra, Kalagnanam, Jayant
Large pre-trained models excel in zero/few-shot learning for language and vision tasks but face challenges in multivariate time series (TS) forecasting due to diverse data characteristics. Consequently, recent research efforts have focused on develop
Externí odkaz:
http://arxiv.org/abs/2401.03955
Autor:
Palaskar, Santosh, Ekambaram, Vijay, Jati, Arindam, Gantayat, Neelamadhav, Saha, Avirup, Nagar, Seema, Nguyen, Nam H., Dayama, Pankaj, Sindhgatta, Renuka, Mohapatra, Prateeti, Kumar, Harshit, Kalagnanam, Jayant, Hemachandra, Nandyala, Rangaraj, Narayan
The efficiency of business processes relies on business key performance indicators (Biz-KPIs), that can be negatively impacted by IT failures. Business and IT Observability (BizITObs) data fuses both Biz-KPIs and IT event channels together as multiva
Externí odkaz:
http://arxiv.org/abs/2310.20280
Transformers have gained popularity in time series forecasting for their ability to capture long-sequence interactions. However, their high memory and computing requirements pose a critical bottleneck for long-term forecasting. To address this, we pr
Externí odkaz:
http://arxiv.org/abs/2306.09364
Autor:
Raykar, Vikas C., Jati, Arindam, Mukherjee, Sumanta, Aggarwal, Nupur, Sarpatwar, Kanthi, Ganapavarapu, Giridhar, Vaculin, Roman
A trustworthy machine learning model should be accurate as well as explainable. Understanding why a model makes a certain decision defines the notion of explainability. While various flavors of explainability have been well-studied in supervised lear
Externí odkaz:
http://arxiv.org/abs/2303.12316
Autor:
Jati, Arindam, Ekambaram, Vijay, Pal, Shaonli, Quanz, Brian, Gifford, Wesley M., Harsha, Pavithra, Siegel, Stuart, Mukherjee, Sumanta, Narayanaswami, Chandra
Selecting the right set of hyperparameters is crucial in time series forecasting. The classical temporal cross-validation framework for hyperparameter optimization (HPO) often leads to poor test performance because of a possible mismatch between vali
Externí odkaz:
http://arxiv.org/abs/2211.15092
Autor:
Pal, Monisankha, Jati, Arindam, Peri, Raghuveer, Hsu, Chin-Cheng, AbdAlmageed, Wael, Narayanan, Shrikanth
Deep neural network based speaker recognition systems can easily be deceived by an adversary using minuscule imperceptible perturbations to the input speech samples. These adversarial attacks pose serious security threats to the speaker recognition s
Externí odkaz:
http://arxiv.org/abs/2010.16038
Autor:
Jati, Arindam, Hsu, Chin-Cheng, Pal, Monisankha, Peri, Raghuveer, AbdAlmageed, Wael, Narayanan, Shrikanth
Robust speaker recognition, including in the presence of malicious attacks, is becoming increasingly important and essential, especially due to the proliferation of several smart speakers and personal agents that interact with an individual's voice c
Externí odkaz:
http://arxiv.org/abs/2008.07685
The primary characteristic of robust speaker representations is that they are invariant to factors of variability not related to speaker identity. Disentanglement of speaker representations is one of the techniques used to improve robustness of speak
Externí odkaz:
http://arxiv.org/abs/2002.03520