Arham Amin's banner

Arham Amin

@arhamamiin • 2,411 subscribers

20. building. https://t.co/jf5GVJioMo (100k+ users), anonymous(200k+ users) and more | sidequest @whoburnedmore

Shorts

Day 12 of learning AI bs from scratch > a look into recurrent neural networks (RNN's) > learned about Long Short-Term Memory > read couple chapters of > drawbacks of RNN's > Simple Neural networks → CNN → RNN will try and train one MLP, CNN and a RNN from scratch next and try and summarize its working it a blog. back to doing based learning after this, much more retention like that.

Day 12 of learning AI bs from scratch > a look into recurrent neural networks (RNN's) > learned about Long Short-Term Memory > read couple chapters of > drawbacks of RNN's > Simple Neural networks → CNN → RNN will try and train one MLP, CNN and a RNN from scratch next and try and summarize its working it a blog. back to doing based learning after this, much more retention like that.

62,415 次观看

Day 15 of learning AI bs from scratch > looked into seq2seq models > understood the encoder-decoder architecture > implemented a basic Seq2Seq model using RNNs > how the decoder generates outputs one step at a time > read couple more chapters of > understood the fixed-context bottleneck I updated the resource list blog, link below, it has more resources organized now. Fell asleep on the desk towards the morning, rweeting rn after waking up.

Day 15 of learning AI bs from scratch > looked into seq2seq models > understood the encoder-decoder architecture > implemented a basic Seq2Seq model using RNNs > how the decoder generates outputs one step at a time > read couple more chapters of > understood the fixed-context bottleneck I updated the resource list blog, link below, it has more resources organized now. Fell asleep on the desk towards the morning, rweeting rn after waking up.

31,853 次观看

Videos

Anya Rossi

sweetdream.ai

SweetDream.ai•Sponsored•Livecam

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

Exclusive private shows

1.2k viewers online

Private Show

Join now for exclusive access

Free preview available • Premium content

Day 27 of learning AI bs from scratch > reading more into Transformer training > looked into tokenization, context windows and next-token prediction > went through more around how batching + sequence length affect training > read parts of Sebastian Raschka’s LLM-from-scratch material > went through some of the Hugging Face LLM course around tokenizers + a bunch of gaps before going back into implementation Mostly reading again, but understanding the training side much better now. Sleep cycle is cooked. Also caught an amazing sunset today good references: my current roadmap below. more building next.

Day 27 of learning AI bs from scratch > reading more into Transformer training > looked into tokenization, context windows and next-token prediction > went through more around how batching + sequence length affect training > read parts of Sebastian Raschka’s LLM-from-scratch material > went through some of the Hugging Face LLM course around tokenizers + a bunch of gaps before going back into implementation Mostly reading again, but understanding the training side much better now. Sleep cycle is cooked. Also caught an amazing sunset today good references: my current roadmap below. more building next.

13,211 次观看 • 1 个月前

没有更多内容可加载