´ëÇѱݼӷÀç·áÇÐȸ Àü»êÀç·á°úÇкаú¿¡¼´Â 'Àü»êÀç·á°úÇÐ ÇÏ°è ½ÉÆ÷Áö¾ö'À» ¾Æ·¡¿Í °°ÀÌ °³ÃÖÇÏ¿À´Ï ¿¬±¸ÀÚ ¿©·¯ºÐÀÇ ¸¹Àº Âü¿©¸¦ ºÎŹµå¸³´Ï´Ù. À̹ø ½ÉÆ÷Áö¾öÀº '»ý¼º/´Éµ¿Çü ÀΰøÁö´É±â¹Ý Àü»êÀç·á°úÇÐ'¸¦ ÁÖÁ¦·Î ÀΰøÁö´É ¹× Àü»êÀç·á°úÇÐ ºÐ¾ß 13¸íÀÇ Àü¹®°¡ ÃÊû°¿¬À¸·Î ÁøÇàÇÕ´Ï´Ù. ¡áÁÖÃÖ : ´ëÇѱݼӷÀç·áÇÐȸ Àü»êÀç·á°úÇкаú ¡áÀÏÀÚ : 2024³â 6¿ù 27ÀÏ (¸ñ) ~ 6¿ù 29ÀÏ (Åä) ¡áÀå¼Ò : °í·Á´ëÇб³ °øÇаü 566È£ ¡á½ÉÆ÷Áö¾ö ÁÖÁ¦ : »ý¼º/´Éµ¿Çü ÀΰøÁö´É±â¹Ý Àü»êÀç·á°úÇÐ ¡áµî·Ï : (Ŭ¸¯ ½Ã »çÀüµî·Ï ÆäÀÌÁö·Î À̵¿) µî·Ï¹æ½Ä | ÀÏ¹Ý µî·Ïºñ | Çлý µî·Ïºñ | »çÀüµî·Ï (6¿ù20ÀÏ ±îÁö) | 150,000¿ø | 80,000¿ø | ÇöÀåµî·Ï (6¿ù27ÀÏ~28ÀÏ) | 200,000¿ø | 100,000¿ø |
- »çÀüµî·ÏÀº 6¿ù20ÀÏ ±îÁö ÇÐȸȨÆäÀÌÁö¿¡¼ ½Åû (Ãë¼Ò ¹× ȯºÒÀº 6¿ù21ÀÏ ±îÁö¸¸ °¡´É)
- ÇöÀåµî·ÏÀº 6¿ù 27ÀÏ ¹× 28ÀÏ ÇöÀå¿¡¼ °¡´É
- µî·Ïºñ¿¡´Â 27ÀÏ ¼®½Ä ¹× 28ÀÏ Áᫎ Æ÷ÇÔÀÌ¸ç ¼÷¹Úºñ Á¦¿Ü
¡áÇÁ·Î±×·¥ : 6¿ù 27ÀÏ ¸ñ¿äÀÏ | 13:00 - 13:30 | µî·Ï ¹× Çà»çÀå ¾È³» | ±è¿ëÁÖ (°í·Á´ë) | 13:30 - 13:40 | °³È¸»ç | ±Ç¿ë¿ì (È«ÀÍ´ë) | Session 1: General materials design using AI | ÁÂÀå: TBA | 13:40 - 14:10 | AI È°¿ë OLED ¼³°è¹æÇâ - Àç·á & ¼ÒÀÚ | ¾çÁßȯ (LGµð½ºÇ÷¹ÀÌ) | 14:10 - 14:40 | GNN-based modeling for novel catalyst developments | ±èµ¿ÈÆ (KIST) | 14:40 - 15:10 | ÅëÇÕÀü»êÀç·á°øÇаú ÀΰøÁö´ÉÀ» È°¿ëÇÑ °í¼º´É ³»Áø³»È° ¼³°è | ±è°æ´ö (POSTECH) | 15:10 - 15:40 | ±â°èÇнÀÀ» È°¿ëÇÑ ¼ÒÀç °áÁ¤±¸Á¶ ¿¹Ãø | °¼º¿ì (KIST) | 15:40 - 16:00 | Coffee Break | ¡¡ | Session 2: Materials design using generative and large language model | ÁÂÀå: TBA | 16:00 - 16:30 | Inverse design of molecule: Generative Chemical Transformer to reinforcement learning-guided combinatorial chemistry | ³ªÁ¾°É (ÀÌÈ¿©´ë) | 16:30 - 17:00 | »ý¼ºÇü ÀΰøÁö´ÉÀ» È°¿ëÇÑ À¯¹«±â ¼ÒÀç¼³°è | ³ëÁÖȯ (KRICT) | 17:00 - 17:30 | Inverse Design of MOFs: From ChatGPT to Quantum Computing | ±èÁöÇÑ (KAIST) | 17:30 - 18:00 | One-Shot Heterogeneous Transfer Learning from Calculated Crystal Structures to Experimentally Observed Materials | ³ª°æ¼® (KRICT) | 18:00 - 20:00 | Dinner | ¡¡ | 6¿ù 28ÀÏ ±Ý¿äÀÏ | Session 3: AI based catalyst design | ÁÂÀå: TBA | 10:30 - 11:00 | Efficient data sampling for surrogate models of active sites and potential energy surfaces in catalysts design (Zoom) | ÀüÈ£Á¦ (MIT) | 11:00 - 11:30 | Optimization of reaction parameters of a methane conversion using machine learning | ±èÇö¿ì (GIST) | 11:30 - 13:00 | Lunch Break | ¡¡ | Session 4: Active learning based materials design and machine learning potential | ÁÂÀå: TBA | 13:00 - 13:30 | ´Éµ¿ÇнÀ ±â¹Ý ±â°èÇнÀ Æ÷ÅÙ¼È °³¹ß ¹× È°¿ë | ÀÌ»ó¿í (¼º±Õ°ü´ë) | 13:30 - 14:00 | Searching for EUV-sensitive organic molecules with pre-trained graph neural networks and Bayesian active learning | ÇϹοµ (SAIT) | 14:00 - 14:30 | Bayesian approaches for uncertainty quantification of deep learning machine learning potential | ¸íâ¿ì (¼º±Õ°ü´ë) | 14:30 - 16:00 | Á¾ÇÕ ÅäÀÇ, »çÁøÃÔ¿µ ¹× Æóȸ»ç | ¡¡ | 6¿ù 29ÀÏ Åä¿äÀÏ | 10:00 - 12:00 | Àü»êÀç·á°úÇкаú °Ü¿ï ½ÉÆ÷Áö¾ö ÀÏÁ¤ ¹× ÅäÀÇ | ¡¡ |
¡á½ÉÆ÷Áö¾ö Á¶Á÷À§¿øȸ: À§¿øÀå : ±è¿ëÁÖ ±³¼ö (°í·Á´ëÇб³) À§¿ø : ±Ç¿ë¿ì ±³¼ö (È«ÀÍ´ëÇб³), °¿µÈ£ ±³¼ö (ÀÎõ´ëÇб³), ¹é¼ÀÎ ±³¼ö (¼°´ëÇб³), ½ÅÇý¿µ ±³¼ö (Ãæ³²´ëÇб³), °ÁØÈñ ±³¼ö (ºÎ»ê´ëÇб³) ¹®ÀÇ : ±è¿ëÁÖ ±³¼ö (°í·Á´ëÇб³ ½Å¼ÒÀç°øÇкÎ) : cjyjee@korea.ac.kr °ÁØÈñ ±³¼ö (ºÎ»ê´ëÇб³ ³ª³ë¿¡³ÊÁö°øÇаú) : j.kang@pusan.ac.kr µî·Ï¹®ÀÇ : ¾ç¼¼Àº ´ë¸® (´ëÇѱݼӷÀç·áÇÐȸ) : kimhak@kim.or.kr ¡áÁÖÃÖ : ´ëÇѱݼӷÀç·áÇÐȸ Àü»êÀç·á°úÇкаú À§¿øÀå : ±Ç¿ë¿ì ±³¼ö ºÎÀ§¿øÀå : À̵¿È ±³¼ö Ãѹ«°£»ç : ±èÇöÀ¯ ±³¼ö, ±èÇüÁØ ±³¼ö ¡áÀå¼Ò¾È³»: °í·Á´ëÇб³ °øÇаü 566È£ (ÁöÇÏö 6È£¼± ¾È¾Ï¿ª 4¹øÃⱸ¿¡¼ µµº¸·Î 10ºÐ³»)
*÷ºÎÆÄÀÏ:
¿©¸§Çб³_°¡¾È_ÃÖÁ¾_ver2.pdf
|