Lecture

Optical Computing: All-Analog Photoelectronic Chip for Vision Tasks

Related lectures (32)

Explores the optimization of neuroprosthetic systems, including sensory feedback restoration and neural stimulation strategies.

Neural Signal Compression

Explores analog-to-digital conversion, neural signal optimization, multichannel architectures, and on-chip compression techniques in neuroengineering.

Optical Machine Learning: Harnessing Multiple Scattering for Efficiency

Explores the use of optics in machine learning, focusing on large-scale random matrix multiplication through multiple scattering of light.

Machine Learning Fundamentals

Covers fundamental principles, opportunities, and challenges in machine learning.

Neural Architectures for Embodied AI and Cognition

Explores neural architectures for embodied AI, cognitive systems, and the integration of computing and robotics.

Neural Signals and Signal Processing

Explores neural signals, EMG control, muscle synergies, and HD-EMG for prosthetic devices.

Perception: Data-Driven Approaches

Explores perception in deep learning for autonomous vehicles, covering image classification, optimization methods, and the role of representation in machine learning.

Neural Signals and Signal Processing

Covers neural signals, brain enthusiasm, neuroimaging, and statistical analysis in neuroimaging studies.

Computer Vision: Fundamentals and Applications

Covers the fundamentals of computer vision, illusions, challenges, applications, and history.

Convolutional Neural Networks

Covers convolutional neural networks, filter operations, and their applications in signal processing and image analysis.

Ground Penetrating Radar: Data Analysis

Explores the automated picking of reinforcement bars within Ground Penetrating Radar data using machine learning and signal processing techniques.

Watermarking II

Covers advanced topics in watermarking, including resisting scaling and rotations, self-referenced watermarking, and types of attacks.

Project-Based Learning in Communications and Robotics

Introduces a project-based course in communications and robotics, emphasizing practical projects and independent learning to prepare students for real-world challenges.

Second-Order Model Compression

Explores second-order model compression for massive deep neural networks, showcasing compression techniques and their impact on model accuracy.

Adaptive Signal Processing: Filtering & Neural Networks

Explores adaptive signal processing, gradient descent, and the LMS algorithm for efficient filtering and neural network training.

Radar Technologies: Applications and Challenges in Robotics

Discusses radar technologies, their applications in robotics, and challenges in mmWave imaging.

Introduction to Signals and Filters

Covers the conversion of analog signals to digital, data compression, and signal reconstruction, highlighting the significance of signal processing in communication systems.

Neural Signals and Signal Processing

Explores nuclear magnetic resonance, MRI principles, pulse sequences, image reconstruction, safety considerations, and volume normalization in brain imaging.

Data Compression: Sparse Signals and Data Recording

Explores data compression through signal sparsity, questioning the need for recording vast amounts of data.

Neural Signals and Signal Processing

Delves into neural signals, GLM, ANOVA, brain mapping, connectivity, and multivariate methods.