I'm Srikanth Machiraju an Architect at Microsoft, Published Author and Independent Researcher. I'm currently learning distributed machine learning and Artificial intelligence. I create a blend of my expertise in building cloud-native solutions with AI / ML to create innovative products. I also write articles on linked-in and towards datascience related to building intelligent apps for cloud and ML. I'm specialized in Large language models, deep reinforcement learning, so if you are looking for tips, quick help or have an interesting project you can always reach out to me.
Here are some of the books I authored.
š« How to reach me: Write to [email protected]
šÆ Iām looking to collaborate on research work related to reinforcement learning.
ā” Fun fact: I'm actually not as busy as it appears :)
sriksmachi/sriksmachi is a āØ distributed ML systems āØ repository where you can find all my work.
Here are some ideas to get you started:
- š Iām currently working on applied RL
- š± Iām currently learning distributed ML systems
- šÆ Iām looking to collaborate on RL in the field of industrial automation
- š¤ Iām looking for help with ...
- š¬ Ask me about ML/DS/AI, designing distributed systems for the cloud, microservices design
- š« How to reach me: [email protected] / linked-in
============================================
============================================
Anomaly detection using PCA | https://github.com/sriksmachi/sriksml/blob/main/pca.ipynb |
Resampling Approaches | https://github.com/sriksmachi/sriksml/blob/main/ResamplingApproaches.ipynb |
Text generation using Simple RNN and Glove Models | https://github.com/sriksmachi/sriksml/blob/main/language-models/rnn-glove-embeddings.ipynb |
Build a transformer from scratch | https://github.com/sriksmachi/sriksml/blob/main/genai/transformers_101_nmt_eng_hin.ipynb |
Variational Auto Encoders | https://github.com/sriksmachi/sriksml/blob/main/genai/variational-auto-encoders.ipynb |
Cycle GANs | https://github.com/sriksmachi/aimriscan |
=============================================
============================================
Building an Azure Quiz using GPT, Chat GPT, and Embeddings models | https://github.com/sriksmachi/openai-samples/tree/main/azure-quiz |
Document classification by fine-tuning Open AI Models | https://github.com/sriksmachi/openai-samples/tree/main/document-classification |
Prompt engineering samples | https://github.com/sriksmachi/openai-samples/tree/main/prompt-engineering |
Build AI Apps using langchain, vector databases, embeddings | https://github.com/sriksmachi/openai-samples/tree/main/complete-ai-app |
Knowledge distillation in large language models | https://github.com/sriksmachi/sriksml/blob/main/language-models/knowledge_distillation_llm.ipynb |
Fine-tuning LLMs using RLHF | https://github.com/sriksmachi/sriksml/blob/main/language-models/fine_tuning_llms_rlhf.ipynb |
==============================================
==============================================
Q-learning | TBD |
REINFORCE | https://github.com/sriksmachi/sriksml/blob/main/reinforcement-learning/reinforce.ipynb |
SARSA | TBD |
DQN | TBD |
DDPG | TBD |
TRPO | TBD |
PPO | https://github.com/sriksmachi/sriksml/blob/main/reinforcement-learning/ppo.ipynb |
Ishara | https://github.com/sriksmachi/ishara |
Octopus | https://github.com/sriksmachi/ishara |
SuperCabs | https://github.com/sriksmachi/supercabs |
RBEI | https://github.com/sriksmachi/rbei |