Videos

Deep Learning in Life Sciences – Lecture 01 – Course Intro, AI, ML (Spring 2021)



Manolis Kellis

6.874/6.802/20.390/20.490/HST.506 Spring 2021 Prof. Manolis Kellis
Deep Learning in the Life Sciences / Computational Systems Biology
Playlist: https://youtube.com/playlist?list=PLypiXJdtIca5sxV7aE3-PS9fYX3vUdIOX
Latest slides and course today: http://compbio.mit.edu/6874
Spring 2021 slides and materials: http://mit6874.github.io/

0:00 Course intro, staff, meeting times, prereqs, grade breakdown, links
07:19 Why Deep Learning in the Life Sciences
23:49 Extracting signal from noise
25:24 Modules: ML, Regulation, Variation, Folding, Imaging, Frontiers
30:36 Lectures, Scribing, Quiz, Guest Lectures
34:10 Projects, mentoring, teams, milestones, papers, resources
51:28 First day survey, year, major, timezone, background, drivers, guidance
54:28 Intelligence, Classical AI, Artificial Intelligence, Machine Learning, Representations
1:00:30 Bayesian Inference, Observed vs. Hidden, Parameter Estimation
1:03:30 Bayes’ Rule, Posterior, Likelihood, Prior, Marginal
1:05:40 Clustering, Classification, Feature Engineering, Feature Learning
1:08:27 Generative (model) vs. discriminative (separators) learning
1:11:09 Classification performance across range of thresholds
1:11:40 Network inference, linear algebra, dimensionality reduction, regularization
1:12:50 AI vs. Machine Learning vs. Representation Learning vs. Deep Learning
1:14:16 Deep representation learning through layers of abstraction
1:14:58 Human vision: layers, abstractions, representations, neuronal firing
1:16:20 Deep multi-layer architectures in mammalian, primate, and human brain
1:17:40 Neural network primitives, neurons, networks, non-linearities, gradient learning
1:18:23 Preview of backpropagation, overfitting, dropout, convolution, autoencoders
1:19:10 Conclusion, Questions, Compute Power of human, Interpretability, Goodbyes

Source

Similar Posts

26 thoughts on “Deep Learning in Life Sciences – Lecture 01 – Course Intro, AI, ML (Spring 2021)
  1. Watching how organised these lectures are, and the quality of the teachers, I realise the quality of education in schools like MIT is huge when compared to other universities in other countries

  2. Thanks for this playlist. Doing great work to democratize knowledge huge respect to you Prof Kellis and to MIT for providing these resources for free

  3. I have watched your 4 talks on lex fridman podcast and just love the way you are able to articulate such ideas smoothly. So, that brought me here. Hope I am able to complete the course virtually.

  4. I was an international college student in Boston, biology major, graduated in 2015, now been studying bioinformatics phD in South Korea. I came across with this video and loved it. Great lectures and very helpful. It reminds me of good times in US and made me want to go back for post-doc if possible. I just want to say thank you professor Kellies for sharing your excellent knowledge and thank you all in class. I really appreciate it.

  5. My neurons was stimulated by the signals from this lecture after sigmoid activation with last output layer the probability of excitement is 95% that was measured by binary accuracy.

Comments are closed.

WP2Social Auto Publish Powered By : XYZScripts.com