Error converting content: marked is not a function
location:: Home - Avalon, Boston victory-hour:: pomodoro-blocks:: wake-up:: day:: icon:: 📅🗓⚡️🌟🌟🌟 - My Daily Mantra: Vachan - I will not argue with other. I will not judge others - **08:36 AM, day. Morning Pages** collapsed:: true - Remember: No Rush - Things top of my mind RenovateAI App - DesignerGPT - answers all design questions - interior design tips - ? - what kind of questions? - read all design encyclopedia, vector indexed - works across countries as needed - RenovateAI App - country specific styles - Morning. -10 F in boston today. Happy saturday. - #mooji/10mins-seeingwithouteyes om 🙏 - 🌟👧 ☕️ 🛏️ 9:15 - 10:45 Day 25 Cont. 🍅🍅🍅 reading mlp paper P/AI Expertise collapsed:: true - #boom these guys had vector embeddings in 2023; solving curse of dimensionality - For example, having seen the sentence “The cat is walking in the bedroom” in the training corpus should help us gener- alize to make the sentence “A dog was running in a room” almost as likely, simply because “dog”and “cat” (resp. “the”and “a”, “room”and “bedroom”, etc...) have similar semantic and grammatical roles - associate with each word in the vocabulary a distributed word feature vector (a real- valued vector in Rm), 2. express the joint probability function of word sequences in terms of the feature vectors of these words in the sequence, and 3. learn simultaneously the word feature vectors and the parameters of that probability function. - In the proposed model, it will so generalize because “similar” words are expected to have a similar feature vector, and because the probability function is a smooth function of these feature values, a small change in the features will induce a small change in the probability. Therefore, the presence of only one of the above sentences in the training data will in- crease the probability, not only of that sentence, but also of its combinatorial number of“neighbors” in sentence space (as represented by sequences of feature vectors). - It is a successful large- scale application of the same idea, along with the (old) idea of learning a distributed representation for symbolic data, that was advocated in the early days of connectionism (Hinton, 1986, Elman, 1990) - In contrast, here we push this idea to a large scale, and concentrate on learning a statistical model ofthe distribution ofword sequences, rather than learning the role ofwords in a sentence. - The idea of discovering some similarities between words to obtain generalization from training sequences to new sequences is not new. each word is associated deterministically or probabilistically with a discrete class, and words in the same class are similar in some respec - In the model proposed here, instead of characterizing the similarity with a discrete random or deterministic variable (which corresponds to a soft or hard partition of the set of words), we use a continuous real-vector for each word, i.e. a learned distributed feature vector, to represent similarity between words - - #Thoughts - A set of key hard problems and solutions - A set key ideas - A set of key jokes - Why name #TrailAndError.AI - fundamental way we learn - elephant 🐘 baby being silly - play == trial and error - 7:30 - 8 AM: #saie/bootime - Bed time with boo. Coffee, reading and fun - 🖥 🛠️ 12 - 12:45 PM: ##log🪵/t&e/ercan📞 - Strategy #RenovateAI App - 1 PM: #Workout/kickboxing with boo - 🥣 📺 🍽 2 - 4 PM: Break Fast - 2 - 7 PM: Massive Indian Food and Movie While working. And some fights :) - #fooddelivery Indian - Movie/Drishyam - movd to v1 aftr watching 20 mins of part 2 and really liking it, - P/The Wedding - Getting the invite email done. ✅ - saiesid.com 80% done ✅ - Break. - 🖥 🛠️ 8 - 10 PM: Focus Work. 🍅🍅🍅 collapsed:: true - #TrialAndError.AI - blog on Substack and embed it to website - https://stackblocks.app/#features - #log🪵/alwaysbelooking - Resume updates. Hate chatgpt. - Applied to Electives - engineer CEO, MIT Sloan. Looks good. - couple of CTO job openings at recruiting agencies - seeing bunch of founder openings from startup studios. Getting hired their really is jumping off plane into 01 visa and hope to build a parachute or a rocket before landing. Why not do it for #TrialAndError.AI? How much money do I need from VC then? At 200K / year, I should be ok. So raising 500K should work hmm. I can then give it 1 dedicated year! hmm. Look where we have come in just 2 weeks! sprint 1 of launching the #RenovateAI App - 🖥 🛠️ 10 - 11: Some Digital Marketing learning on Search Ads. Now honing in on US. And pointing at NY users to grok our CPA. - 11 - 2 AM: - Movie/Drishyam 2 - 4.5 stars. Solid. Gripping. I haven’t been this thrilled in a movie! - Wow. Deep. Heart felt. chaturai reminded me of sangrsm. The eyes. Can see why Anil likes the movie. Relates. - In fact this make me emphatic towards introverted non communicative peeps. The problems in like is #dharamyuddh- they cannot lose - Kickoff P/Valentines 2023 - Wedding video - Google prints - **02:09 PM Lights Off** - Late night. Not tight. Like this home chills Saturday night.