MLP Singer

[Priority Research Team Hee-Jo Yoo] TTS (text-to-speech) is a technology that converts text into a voice of a specific voice when inputting arbitrary text. After Google announced the Tacotron series, it quickly switched from HMM (hidden Markov model)-based to deep learning-based, and is now commercially…

Trend Multimodal Few-Shot Learner

Tensorflow VS Pytorch

[Service Development Team Hyeonjun Han] Introduction Tensorflow and PyTorch are the most popular libraries for machine learning. Developers who develop AI services or researchers who study models often face difficulties in selecting a library at the beginning. Also, as the library version goes up...

Trend Multimodal Few-Shot Learner

Eternal light that shines upon a blameless heart

[Prior Research Team Kim Moo-seong] Eternal Sunshine Director Michel Gondry's film 'Eternal Sunshine' is a romantic sci-fi film about memories and parting with Jim Carrey and Kate Winslet as a couple. In the movie, the technology to erase memories comes out...

TrendCodeData Multimodal Few-Shot Learner

Handling Imbalanced Datasets

[Service Development Team Hwang Jun-sun] When supervising machine learning models, when a dataset with an unbalanced number of data between labels is used as training data, the phenomenon in which learning of samples belonging to a label with a small ratio is not performed well you will experience simply…

VisualTrendCode Multimodal Few-Shot Learner

Unity ML-Agents v2.0

[Service Development Team Jeon Jeon-Jun] ML-Agents, unveiled by Unity, is an open source tool that creates virtual characters in the game environment. You can create a game environment and learn NPC characters (Agents) that can operate in the environment through algorithms such as reinforcement learning.…

InteractionTrendData Multimodal Few-Shot Learner

Time Series Data Analysis_TadGAN

[Prior Research Team, Ji-Hyun Song] The TadGAN algorithm developed by the MIT research team is known to have better performance than previously known models in detecting anomalies by analyzing time series data. Currently, many companies researching anomaly detection are working in various fields (financial…