ML Trainings
- Supervised Learning
- Prediction
- Unsupervised Learning
- Clustering
- NLP (Natural Language processing): This is the ability of system to understand natural language
- Terms:
- Input Layers
- Hidden Layers
- Output Layers
- Backpropgation
- Weights
- Biases
- Activation functions
- Embedding: Convert word to vector.
- Embedding Model: A model which has all possible words with vector values
Understanding Text
-
For models to understand text breakthrough happend with
WORD2VEC -
Google was building models for language translation.
-
Google Research introduced transformers and then they submited a research paper ‘Transforms: Attention is all you need’
Popular LLMs
- The below llms are hosted by provider
- OpenAI GPT
- Google Gemini Models
- Microsoft Copilot (indirectly uses openai)
- Anthropic Claude Models
- Opensource LLMS: We can run them on our systems
- Meta LLAMA models
- Ali Qwen Models
- Mistral
- Microsoft Phi Models
- Google Gemma Models
- OpenAI gpt oss models
- Deepseek
