Avatar of 湯沂達.
湯沂達
AI工程師 @ AI Academy
ProfileResume
Posts
0Connections
Print
Avatar of the user.

湯沂達

AI工程師 @ AI Academy
畢業於交通大學應用數學系,現為台灣人工智慧學校的AI工程師。 擔任過台灣人工智慧小聚講者;13組專案之技術指導;IEEE機器學習競賽第二名、TBrain競賽初選通過(複賽進行中)。 擅長於數學建模、機器學習、深度學習、電腦視覺、聲音信號處理、風格轉換。 閒暇時間會閱讀一些AI相關論文、線上論壇、新聞。 近期研究項目 Google Drive Api、Reinforcement Learning、Style Transfer、Audio Tagging、Applied ML Summit、NVIDIA AI Conference
Logo of the organization.
AI Academy
Logo of the organization.
National Chiao Tung University
Taipei, Taiwan

Professional Background

  • Current status
    Employed
  • Profession
  • Fields
  • Work experience
    1-2 years (1-2 years relevant)
  • Management
  • Skills
    Machine Learning
    Tensorflow
    Python
    Computer Vision
    Tensorflow Lite
    Model compression and acceleration
    Mathematic Modeling
    Optimization
    Google Coral
    Google Apps Script
    Google Drive API
    Colab
    Docker
    QT
    tensorflow
    tfmot
  • Highest level of education
    Master

Job search preferences

  • Desired job type
    Full-time
    Interested in working remotely
  • Desired positions
    Machine Learning Engineer
  • Desired work locations
  • Freelance
    Non-freelancer

Work Experience

Logo of the organization.

AI工程師

Jun 2019 - Present
教授學員機器學習、深度學習知識;以技術指導的角色,幫助學員完成AI專案;ML自我進修與產出。 領導學員完成AI專案。(13組專案) 開發入學、內部考試系統、因應疫情之遠端點名系統。 閱讀論文、函式庫,並將之應用在比賽[1, 2]/專案指導[3]/教學文件、讀書會、Meidum、Meetup分享[4-8]/微型專案[9-11]/論文延伸方法提出[12]。 指導專案: 1.聲音的瑕疵檢測與分析 2.RF人體特定動作識別 3.黃光CD線寬預測 4.判斷鏡頭生產品質 5.智慧水表之用水模式辨識 6.以人工智慧為戲劇配樂 7.廢水新砂濾功能辨識系統 8.L5A 2B3T樹脂效率判定與餘命預警 9.Robot cable tray monitor system 10.影片人物的真偽判別 Anti-DeepFake 11.動態物件偵測尋找目標之無人載具 12.智慧手機架 13.購物網站訪客瀏覽行為分析 Reference: [1] (2019) The 2nd Place of IEEE Big Data FEMH Voice Data Challenge 2019 (https://drive.google.com/drive/folders/175LPHjGcpp9qo01KIUqFNkw1PC7a3aO6?usp=sharing) [2] (2021) TBrain-Tomofun 狗音辨識 AI 百萬挑戰賽初賽報告(2021 June:初賽已通過,複賽進行中)(https://drive.google.com/drive/folders/18uk17_LipGpNLEe5f7SljISy0Lupny7j?usp=sharing) [3] (2021) AI專案分享 (https://slides.com/sin_dar_soup/ai#/6/1) [4] (2019) 看見聲音的未來(https://www.facebook.com/groups/datasci.dinner/permalink/2415658465412338/) [5] (2020) Re-Overview Model Compression and Acceleration (https://docs.google.com/presentation/d/1RINEfysY5H-ibBq_Rs6fTnF338gJGQjewyewfwqyas4/edit#slide=id.p) [6] (2020) Transferred/Compact Convolutional Filters (https://slides.com/sin_dar_soup/deck#/transferredcompact-convolutional-filters) [7] (2021) Style Transfer Overview(https://docs.google.com/presentation/d/1wmu9NaUFulkoyG20-eyO7KfHqRgbhdOARPQKQFkpxiU) [8] Medium (https://changethewhat.medium.com/) [9] Download-Google-Drive-Files-From-URLs (https://github.com/mistake0316/Download-Google-Drive-Files-From-URLs) [10] Tomofun 狗音辨識 AI 百萬挑戰賽 classification finetuned on pretrained audio neural networks (PANNs) (https://github.com/mistake0316/panns_transfer_to_Tomfun_6_classes) [11] TF2-Style-Transfer-Collections (https://github.com/mistake0316/TF2-Style-Transfer-Collections) [12] Idea of extension of EagleEye (A good heuristic for filter purning of a model) (https://github.com/anonymous47823493/EagleEye/issues/33)