Engineer Readings – Telegram
[ml][book]

“Self-supervised learning, dubbed “the dark matter of intelligence” 1, is a promising path to advance machine learning. As opposed to supervised learning, which is limited by the availability of labeled data, self-supervised approaches can learn from vast unlabeled data [Chen et al., 2020b, Misra and Maaten, 2020]. Self-supervised learning (SSL) underpins deep learning’s success in natural language processing leading to advances from automated machine translation to large language models trained on web-scale corpora of unlabeled text [Brown et al., 2020, Popel et al., 2020]. In computer vision, SSL pushed new bounds on data size with models such as SEER trained on 1 billion images [Goyal et al., 2021]. SSL methods for computer vision have been able to match or in some cases surpass models trained on labeled data, even on highly competitive benchmarks like ImageNet [Tomasev et al., 2022, He et al., 2020a, Deng et al., 2009]. SSL has also been successfully applied across other modalities such as video, audio, and time series [Wickstrøm et al., 2022, Liu et al., 2022a, Schiappa et al., 2022a].”

https://arxiv.org/abs/2304.12210
[llm]
TELeR: A General Taxonomy of LLM Prompts for Benchmarking Complex Tasks

While LLMs have shown great success in understanding and generating text in traditional conversational settings, their potential for performing ill-defined complex tasks is largely under-studied. Indeed, we are yet to conduct comprehensive benchmarking studies with multiple LLMs that are exclusively focused on a complex task. However, conducting such benchmarking studies is challenging because of the large variations in LLMs' performance when different prompt types/styles are used and different degrees of detail are provided in the prompts. To address this issue, the paper proposes a general taxonomy that can be used to design prompts with specific properties in order to perform a wide range of complex tasks.”

https://arxiv.org/abs/2305.11430
1
[architecture][uber clone]

Juraj Majerik dedicated about 7 months (a total of ~300 hours) to create a simulated version of a ride-sharing app (akin to Uber) as a side project. He described each step in his blog:

https://rides.jurajmajerik.com/system-design
🔥3
[lectures][data science]

CS109A Data Science course materials @Harvard are free and open to everyone!

1. Lecture notes
2. R code, Python notebooks
3. Lab material
4. Advanced sections

https://harvard-iacs.github.io/2019-CS109A/pages/materials.html
👍1