Tech for good

https://www.youtube.com/playlist?list=PLIivdWyY5sqIlLF9JHbyiqzZbib9pFt4x Generative AI Learning Path https://goo.gle/LearnGenAI www.youtube.com Introduction 1. Pass images to encoder 2. Extract information from the images 3. Create some feature vectors 4. Vectors are passed to the decoder 5. Build captions by generating words, one by one. Decoder It gets words one by one and makes the informatio..

https://www.youtube.com/playlist?list=PLIivdWyY5sqIlLF9JHbyiqzZbib9pFt4x Generative AI Learning Path https://goo.gle/LearnGenAI www.youtube.com If you are an app developer or data scientist and want to build an application, you can use Generative AI Studio to quickly prototype and customize generative AI models with no code or low code. If you are a data scientist or ML developer who wants to bu..

https://www.youtube.com/playlist?list=PLIivdWyY5sqIlLF9JHbyiqzZbib9pFt4x Generative AI Learning Path https://goo.gle/LearnGenAI www.youtube.com RNN/LSTM -> Sequence-to-sequence model i.e. Translation, Text classification Although all the models before Transformers were able to represent words as vectors, these vectors did not contain the context. And the usage of words changes based on the conte..

https://www.youtube.com/playlist?list=PLIivdWyY5sqIlLF9JHbyiqzZbib9pFt4x Generative AI Learning Path https://goo.gle/LearnGenAI www.youtube.com Attention mechanism is behind all the transformer models and which is core to the LLM models. Encoder-Decoder is a popular model that is used to translate sentences. The encoder-decoder takes one word at a time and translates it at each time step. Howeve..

https://www.youtube.com/playlist?list=PLIivdWyY5sqIlLF9JHbyiqzZbib9pFt4x Generative AI Learning Path https://goo.gle/LearnGenAI www.youtube.com Encoding stage It produces a vector representation of the input sentence. Decoding stage It creates the sequence output. Both the encoder and the decoder can be implemented with different internal architectures. The internal mechanism can be a recurrent ..

https://www.youtube.com/playlist?list=PLIivdWyY5sqIlLF9JHbyiqzZbib9pFt4x Generative AI Learning Path https://goo.gle/LearnGenAI www.youtube.com GANs One neural network (Generator) -> creates images The other neural network (Discriminator) -> predicts if the image is real or fake Forward diffusion Start with a clean image and add noise iteratively Reverse diffusion Start with a noisy image and re..

https://www.youtube.com/playlist?list=PLIivdWyY5sqIlLF9JHbyiqzZbib9pFt4x Generative AI Learning Path https://goo.gle/LearnGenAI www.youtube.com Google will not design or deploy AI in these four application areas:

https://www.youtube.com/playlist?list=PLIivdWyY5sqIlLF9JHbyiqzZbib9pFt4x Generative AI Learning Path https://goo.gle/LearnGenAI www.youtube.com Pre-trained: for general purpose with a large data set Fine-tuned: for specific aims with a much smaller data set Transformer model (e.g. PaLM) A transformer model consists of encoder and decoder. Encoder - encodes the input sequence and passes it to the..

https://www.youtube.com/playlist?list=PLIivdWyY5sqIlLF9JHbyiqzZbib9pFt4x Generative AI Learning Path https://goo.gle/LearnGenAI www.youtube.com semi-supervised learning = 소량의 labeled data + 대량의 unlabeled data The labeled data -> neural network이 task의 basic concepts을 알 수 있게 도와줌. The unlabeled data -> neural network이 새로운 예시들을 일반화할 수 있게 도와줌.

안녕하세요. 오늘은 Azure Machine Learning로 자동화된 기계 학습(Auto ML)을 사용하는 방법에 대해 알아보겠습니다. 아래의 문서를 참고하여 작성하였습니다. https://docs.microsoft.com/ko-kr/learn/paths/create-no-code-predictive-models-azure-machine-learning/?WT.mc_id=AI-MVP-5003937 Azure Machine Learning에서 시각적 도구를 사용하여 기계 학습 모델 만들기 - Learn Azure Machine Learning에서 시각적 도구를 사용하여 기계 학습 모델 만들기 docs.microsoft.com 1. 소개 Machine Learning(기계학습; 머신러닝)은 대부분의 인공지..