𝗿𝗮𝗺𝗮𝗸𝗿𝘂𝘀𝗵𝗻𝗮— 𝗲/𝗮𝗰𝗰
@techwith_ram • 12,876 subscribers
Sr. DS • AI Updates • Latest news & AI tools • Views are my own
Videos
This is a great lecture at MIT by David Shirokoff on Markov Chains. He covers the fundamentals of Markov Chains using a simple particle movement example. He starts by explaining how a particle moves between two positions, A & B, with different probabilities. From there, the talk converts the problem into matrix form using a Markov matrix. The main topics covered are: - Transition probabilities - Markov matrices - Probability vectors - Matrix multiplication in Markov Chains - Finding probabilities after n steps - Eigenvalues and eigenvectors - Matrix diagonalization - Long-term steady state distribution
𝗿𝗮𝗺𝗮𝗸𝗿𝘂𝘀𝗵𝗻𝗮— 𝗲/𝗮𝗰𝗰141,930 Aufrufe • vor 3 Monaten
If you have time, watch the MIT lecture on Jacobian Matrices by Alan Edelman & Steven G. Johnson, & honestly, it may changes how you look at derivatives. Instead of treating derivatives as just formulas, they explain them as transformations of space. With proper rotation of images on live classes. haha Things they covered: - Difference between linear and non-linear transformations - How matrices act like operators that reshape geometry - Why the Jacobian is the best local linear approximation of a function - Understanding derivatives in higher dimensions - Intuition behind chain rule and automatic differentiation - Early foundations of backpropagation in ML One of the best parts was seeing how tiny input changes propagate through transformations mathematically. A really solid lecture if you want to build deeper intuition behind AI, optimization, and neural networks beyond just coding models. Full video link in comment.
𝗿𝗮𝗺𝗮𝗸𝗿𝘂𝘀𝗵𝗻𝗮— 𝗲/𝗮𝗰𝗰60,360 Aufrufe • vor 3 Monaten
Dumb loops beat clever workflows. A great talk about Ralph Loops. Build Dumb AI Loops That Ship by Chris Parsons. Most teams building with AI agents reach for multi-agent orchestration, planning graphs, and elaborate tool chains. Then they spend months debugging them. A single loop that processes one ticket at a time, evaluates its own output, and improves on the next run will outperform all of it.
𝗿𝗮𝗺𝗮𝗸𝗿𝘂𝘀𝗵𝗻𝗮— 𝗲/𝗮𝗰𝗰23,908 Aufrufe • vor 2 Monaten
This lecture was a really simple & practical introduction to how machines learn Bayesian Learning, Bayes Theorem, Naive Bayes from Kimia Lab by Professor H.R.Tizhoosh. The lecture also walks through - MAP - Maximum Likelihood - Bayes Optimal Classifier - Naive Bayes model A really beginner-friendly lecture if you want to understand how probability thinking shaped modern machine learning.
𝗿𝗮𝗺𝗮𝗸𝗿𝘂𝘀𝗵𝗻𝗮— 𝗲/𝗮𝗰𝗰14,816 Aufrufe • vor 3 Monaten
Keine weiteren Inhalte verfügbar