fullscreen background
Skip to main content

Summer Quarter

Summer Registration Opens May 18
shopping cart icon0

Courses


« Back to Professional & Personal Development

TECH 77 — Modern AI Architectures: From RNNs to Chatbots

Quarter: Summer
Instructor(s): Ishaani Priyadarshini
Duration: 8 weeks
Location: Online
Date(s): Jul 8—Aug 26
Class Recording Available: Yes
Class Meeting Day: Wednesdays
 
Class Meeting Time: 6:00—7:30 pm (PT)
Tuition: $470
   
Refund Deadline: Jul 10
 
Unit(s): 1
   
Status: Registration opens May 18, 8:30 am (PT)
 
Quarter: Summer
Day: Wednesdays
Duration: 8 weeks
Time: 6:00—7:30 pm (PT)
Date(s): Jul 8—Aug 26
Unit(s): 1
Location: Online
 
Tuition: $470
 
Refund Deadline: Jul 10
 
Instructor(s): Ishaani Priyadarshini
 
Recording Available: Yes
 
Status: Registration opens May 18, 8:30 am (PT)
 
 
Artificial intelligence did not emerge fully formed with ChatGPT. It evolved through a series of architectural breakthroughs that reshaped how machines process language and learn from data. This course traces that technical evolution, offering a structured framework for understanding how modern language models came to be.

Designed for students with prior exposure to machine learning, the course examines five pivotal shifts in AI architecture, beginning with the limitations of recurrent neural networks (RNNs) and the emergence of encoder-decoder models for sequence-to-sequence learning. From there, we explore attention mechanisms, the transformer architecture, and the rise of large-scale pretraining and fine-tuning, including developments such as ULMFiT, BERT, and GPT.

Throughout, technical concepts are examined at the architectural level, linking design decisions to the capabilities and constraints of today’s chatbots and generative systems. By the end, participants gain a deeper understanding of the models shaping contemporary AI and the trade-offs driving future innovation.

Students should have prior exposure to core machine learning concepts, including supervised learning, model training, and evaluation. Familiarity with neural networks, particularly feedforward and recurrent models, is recommended. Proficiency in Python is required, as the course includes hands-on coding using libraries such as TensorFlow or PyTorch.

ISHAANI PRIYADARSHINI
Scholarly Assistant Professor, School of Electrical Engineering & Computer Science, Washington State

Ishaani Priyadarshini received a PhD in electrical and computer engineering from the University of Delaware, where she focused on technological singularity. She completed postdoctoral research at UC Berkeley, exploring trustworthy and fair AI systems. She has taught at UC Berkeley's School of Information and was a course facilitator for Cornell’s online certificate programs known as eCornell. She specializes in AI, data science, and cybersecurity.