I’ve completed several courses from DeepLearning and Coursera for Artificial Intelligence and Deep Learning using Python. Today’s methods are quite different from the biometrics research and natural language processing I was focused on early in my career (IBM Research’s Watson Center in Yorktown Heights, Speechworks Intl, and VoiceVerified Inc).
One of the most interesting topics is multi-head masked self-attention in transformers. That has got to be one of the most remarkable breakthroughs in computer science of our time. There’s also backpropagation at the core of neural networks which is optimizing a cost function using derivatives from calculus. If you think about it, that is really incredible also. Backprop for neural networks was invented way back in the 1970’s. I wonder if those researchers could have imagined what AI looks like today and that it scales so well.
Natural Language Processing with Attention Models
Use encoder-decoder, causal, & self-attention to machine translate complete sentences, summarize text, and answer questions.
https://www.coursera.org/account/accomplishments/certificate/39R93C6PG2K3
Natural Language Processing with Sequence Models
Use recurrent neural networks, LSTMs, GRUs & Siamese networks in TensorFlow for sentiment analysis, text generation & named entity recognition.
https://www.coursera.org/account/accomplishments/certificate/FJTVCXJ2EZMQ
Natural Language Processing with Probabilistic Models
Use dynamic programming, hidden Markov models, and word embeddings to implement autocorrect, autocomplete & identify part-of-speech tags for words.
https://www.coursera.org/account/accomplishments/certificate/NQB2RM5MQR2R
Natural Language Processing with Classification and Vector Spaces
Use logistic regression, naïve Bayes, and word vectors to implement sentiment analysis, complete analogies & translate words.
https://www.coursera.org/account/accomplishments/certificate/CNAT67ZYNBA2
Sequence Models
Deep Learning, Hugging Face, Embeddings, Fine-tuning, Large Language Modeling, Artificial Neural Networks, Recurrent Neural Networks (RNNs), Transfer Learning, Generative AI, Natural Language Processing
https://www.coursera.org/account/accomplishments/certificate/22FN5NM7SZ6Q
Convolutional Neural Networks
Feature Engineering, Embeddings, Artificial Neural Networks, Model Training, Deep Learning, Convolutional Neural Networks, Image Analysis, Fine-tuning, Transfer Learning, Tensorflow, Network Architecture, Computer Vision
https://www.coursera.org/account/accomplishments/certificate/BTG9PEYCXT6D
Structuring Machine Learning Projects
AI Product Strategy, Applied Machine Learning, Model Training, Machine Learning Methods, Model Optimization, Artificial Intelligence and Machine Learning (AI/ML), Model Evaluation, Machine Learning, Debugging, Transfer Learning, AI Workflows, Deep Learning
https://www.coursera.org/account/accomplishments/certificate/EMU4U7MVBPK8
Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization
Model Evaluation, Artificial Intelligence and Machine Learning (AI/ML), Artificial Neural Networks, Model Training, Deep Learning, Debugging, Tensorflow, Performance Tuning, Model Optimization, Machine Learning Methods, Applied Machine Learning, Verification And Validation
https://www.coursera.org/account/accomplishments/certificate/JDNU4ELTQ4Z5
Neural Networks and Deep Learning
Applied Machine Learning, Supervised Learning, Machine Learning Methods, Convolutional Neural Networks, Artificial Intelligence and Machine Learning (AI/ML), Artificial Neural Networks, Python Programming, Deep Learning, Artificial Intelligence, Model Training, Model Optimization
https://www.coursera.org/account/accomplishments/certificate/5ESUBYG4LKYD