Tensorflow: A 6-step learning journey
Learn Tensorflow in 6 easy steps. After watching this video, you will learn about tensors, variables, doing forward pass, backward pass (backpropagation), training a model, making graphs and saving everything! P.S. I was on less than 3 hours of sleep (that's how hackathon organizing goes the night before the event, haha) so please forgive me if I sound tired.
Confidential Computing: Keeping your data safe with Google Cloud
This video introduces and explains confidential computing, a hardware-based technology that protects data while it is being used, unlike traditional encryption methods that primarily secure data at rest or in transit. The video emphasizes that confidential computing, using techniques like secure encrypted virtualization (SEV), creates isolated environments called enclaves within the computer's memory to protect sensitive data and code even from cloud providers like Google
Learning Machine Learning: Basics
This video is a tutorial on basic machine learning concepts and models, including supervised and unsupervised learning techniques. The tutorial covers the K-Nearest Neighbors (KNN) algorithm, Support Vector Machine (SVM) classification, and the K-Means clustering algorithm, and demonstrates how to implement these models using Python libraries like Scikit-learn. It uses the Iris dataset, which contains measurements of different iris flower species, to illustrate the principles of classification and clustering. The video also includes an introduction to linear regression for predicting a continuous variable, exemplified by predicting house prices in California.
Learning Machine Learning: Advanced
This video is a tutorial about neural networks, specifically focusing on multi-layer perceptrons (MLPs) and convolutional neural networks (CNNs), and how these machine learning models can be used to solve non-linear classification problems like handwritten digit recognition. The video explains the core concepts of neural networks including perceptrons, activation functions, weights, cost functions, gradient descent, and backpropagation, then shows how these concepts are applied to build and train an MLP model to classify handwritten digits from the MNIST dataset using the Python programming language in Google Colab.
Intro to Deep Learning Frameworks: TensorFlow & PyTorch
The video compares TensorFlow and PyTorch, focusing on TensorFlow’s graph-based design and efficient data input pipelines. It explains concepts like prefetching, caching, and TensorBoard for optimizing training. The video concludes by highlighting TensorFlow’s production-readiness and PyTorch’s ease of use for rapid prototyping and NLP.
DISCO: Diversity and Improvisation through Stories in COmmunity
This is a fun talk that dives deeper into the importance of building soft skills alongside hard technical ones. It conveys the importance of community, storytelling, and self-improvisation and encourages people from technical as well as non-technical backgrounds to look beyond tech and technical tools. P.S. Sorry for the relatively poor audio and video quality on this one.
Many other talks, like the TedAI panel, HackDavis panel, Intro to Web-scraping, and Lessons Learnt from a Boat's Life among others, were either not recorded or are yet to be uploaded. If you'd like the slides or materials for any of them, just reach out.