Gave a talk at Google Next 2018 about machine learning.
Talk includes usage of the following for applied machine learning in context of media and news publishing.
- BigQuery
- BQML
- Google NLP
- Google Sound
- AutoML
- TensorFlow
- Spark
The Thinking Node
Gave a talk at Google Next 2018 about machine learning.
Talk includes usage of the following for applied machine learning in context of media and news publishing.
The emergence of large language models, such as ChatGPT, has revolutionized the field of natural language processing and has paved the way for new applications and advancements in artificial intelligence.
In the past, language models were limited by the size of the data they were trained on and the computational resources available. However, with advances in hardware and the availability of large amounts of data, researchers have been able to train much larger language models that can generate human-like text and perform a wide range of language tasks with unprecedented accuracy.
One of the most well-known large language models is ChatGPT, developed by OpenAI. ChatGPT is a conversational AI model trained on a diverse range of text, including books, websites, and social media. It uses a transformer architecture and is capable of generating text that is coherent and context-sensitive.
ChatGPT has been used for a variety of applications, including chatbots, language translation, question-answering, and summarization. It has been integrated into many platforms, such as customer service chatbots, and has proven to be an effective tool for automating and streamlining communication.
A simple technique to improve problem solving capabilities of LLM such as GPT3 is to use chain of thought prompting . In this technique a human labeler feeds in intermediate steps in response prompts (see example below), like a teacher encourages its student to explain the reasoning. The model can then can learn to reason on unseen problems, and improve its ability to answer questions that require multi step reasoning. This also helps a user to understand the thought process and how the model derived the answer.
https://ai.googleblog.com/2022/05/language-models-perform-reasoning-via.html
Blog by Jeff Dean, mentions power of chain of prompt reasoning
https://ai.googleblog.com/2023/01/google-research-2022-beyond-language.html
https://twimlai.com/twiml-talk-182-applied-machine-learning-for-publishers-with-naveed-ahmad/
My Podcast interview about machine learning, my talk at Google Next by Sam Charrington
Gave a talk about BQML along with Abhishek product manager of AI at Google. Democratization of AI via BigQuery.
Google launches Google News initiative to promote quality journalism via technology
https://newsinitiative.withgoogle.com/
Case study, featuring my work using Google Cloud, Machine Learning and BigQuery
This is a case study published of my groups work using machine learning in journalism
Mention of my work applied machine learning at Hearst on this Google blog post
https://www.blog.google/topics/journalism-news/how-publishers-can-take-advantage-machine-learning/
Have been reading research work for recommendation engine, specifically that can be used to do better news/blog recommendations.
Links on work in this area including open source code.
https://github.com/tensorflow/tensorflow/tree/r1.2/tensorflow/contrib/ios_examples
Just ran first ran deep learning model with the camera app example. Pretty good image recognition!!
The next level is object detection, i.e creating a bounding box around detected image.
https://github.com/yjmade/ios_camera_object_detection
Deep learning is progressing rapidly. There is a new interesting research paper every other week. This is a list of essential deep learning research by categories.
These are the recent advances for CNN, original was Lecun-5 in the 98 paper mentioned above .
Finding a bounding box around different objects is harder than simply classifying an image. This a class of image localization and detection problems.
One of the hottest areas of research. This is a class of algorithms where 2 neural networks collaborate to generate e.g. realistic images. One network produces fake images (faker), and the other network learns to decipher fake from real (detective). Both networks compete with each other and try to be good at their jobs, till the faker is so good that it can generate realistic images. Fake it till you make it!
Getting labeled data is expensive, while unlabeled data is abundant. Techniques to use little bit of training data and lots of unlabeled data.
Research on being able to ask question on images. e.g. asking if there are there more blue balls than yellow about an image.
Being able to take a picture and a style image e.g. a painting, and redraw the picture in the painting style. See my blog on painting like Picaso.
This is area of unsupervised learning. An auto encoder is a neural network that tries to recreate the original image. e.g. give it any picture and it will try to recreate the same image. Why would anyone want to do that. The neural network tries to learn a condensed representation of images given that there are commonalities. Auto encoders can be used to pre train a neural network with unlabeled data.
Released CatGan code. This was done as last assignment for NYU Deep Learning course, taught by Yann Lecun. This is a conditional GAN, and can train it to generate 4 different types of cats i.e. white, golden, black and mix.
https://github.com/navacron/deeplearning/tree/master/pytorch/catgan
The following is output conditioned on golden cats. By favorite one is 3rd one from the right in the first row. Everytime the GAN is run it will generate unique cats like these. For more cats visit the github page.
Alternate to Deep Reinforcement Learning
Added a setup guide to using GPU on Amazon EC2
I have release ipython tutorial notebooks for neural network using pytorch. Pytorch is implementation of torch in python released by Facebook. This is what is being used in the Deep Learning course that I am taking at NYU, taught by professor Yann Lecun
https://github.com/navacron/deeplearning/tree/master/pytorch
This uses the autograd feature that is unique to pytoch and torch (not available in tensorflow). This is pytorch version of cs231n http://cs231n.github.io/neural-networks-case-study/