Detecting scene types in a movie can be very useful for application such as video editing, ratings assignment, and personalization. We propose a system for detecting kissing scenes in a movie. This system consists of two components. The first component is a binary classifier that predicts a binary label (i.e. kissing or not) given a features exctracted from both the still frames and audio waves of a one-second segment. The second component aggregates the binary labels for contiguous non-overlapping segments into a set of kissing scenes. We experimented with a variety of 2D and 3D convolutional architectures such as ResNet, DesnseNet, and VGGish and developed a highly accurate kissing detector that achieves a validation F1 score of 0.95 on a diverse database of Hollywood films ranging many genres and spanning multiple decades. The code for this project is available at http://github.com/amirziai/kissing-detector. Read More
Monthly Archives: June 2019
Better Future through AI: Avoiding Pitfalls and Guiding AI Towards Its Full Potential
Articial Intelligence (AI) technology is rapidly changing many areas of society. While there is tremendous potential in this transition, there are several pitfalls as well. Using the history of computing and the world-wide web as a guide, in this article we identify those pitfalls and actions that lead AI development to its full potential. If done right, AI will be instrumental in achieving the goals we set for economy, society, and the world in general. Read More
If DARPA Has Its Way, AI Will Rule the Wireless Spectrum
In the early 2000s, Bluetooth almost met an untimely end. The first Bluetooth devices struggled to avoid interfering with Wi-Fi routers, a higher-powered, more-established cohort on the radio spectrum, with which Bluetooth devices shared frequencies. Bluetooth engineers eventually modified their standard—and saved their wireless tech from early extinction—by developing frequency-hopping techniques for Bluetooth devices, which shifted operation to unoccupied bands upon detecting Wi-Fi signals.
Frequency hopping is just one way to avoid interference, a problem that has plagued radio since its beginning. Long ago, regulators learned to manage spectrum so that in the emerging wireless ecosystem, different radio users were allocated different frequencies for their exclusive use. While this practice avoids the challenges of detecting transmissions and shifting frequencies on the fly, it makes very inefficient use of spectrum, as portions lay fallow. Read More
Lecture Notes by Andrew Ng : Full Set
The following notes represent a complete, stand alone interpretation of Stanford’s machine learning course presented by Professor Andrew Ng and originally posted on the ml-class.org website during the fall 2011 semester. The topics covered are shown below, although for a more detailed summary see lecture 19. The only content not covered here is the Octave/MATLAB programming. Read More
Neuroscience-Inspired Artificial Intelligence
The fields of neuroscience and artificial intelligence (AI) have a long and intertwined history. In more recent times, however, communication and collaboration between the two fields has become less commonplace. In this article, we argue that better understanding biological brains could play a vital role in building intelligent machines. We survey historical interactions between the AI and neuroscience fields and emphasize current advances in AI that have been inspired by the study of neural computation in humans and other animals. We conclude by highlighting shared themes that may be key for advancing future research in both fields. Read More
Artificial intelligence-enhanced journalism offers a glimpse of the future of the knowledge economy
Much as robots have transformed entire swaths of the manufacturing economy, artificial intelligence and automation are now changing information work, letting humans offload cognitive labor to computers. In journalism, for instance, data mining systems alert reporters to potential news stories, while newsbotsoffer new ways for audiences to explore information. Automated writing systems generate financial, sports and elections coverage.
A common question as these intelligent technologies infiltrate various industries is how work and labor will be affected. In this case, who—or what—will do journalism in this AI-enhanced and automated world, and how will they do it?
The evidence I’ve assembled in my new book “Automating the New: How Algorithms are Rewriting the Media” suggests that the future of AI-enabled journalism will still have plenty of people around. However, the jobs, roles and tasks of those people will evolve and look a bit different. Human work will be hybridized—blended together with algorithms—to suit AI’s capabilities and accommodate its limitations. Read More
Parameter Efficient Training of Deep Convolutional Neural Networks by Dynamic Sparse Reparameterization
Modern deep neural networks are typically highly over parameterized. Pruning techniques are able to remove a significant fraction of network parameters with little loss in accuracy. Recently, techniques based on dynamic reallocation of non-zero parameters have emerged, allowing direct training of sparse networks without having to pre-train a large dense model. Here we present a novel dynamic sparse reparameterization method that addresses the limitations of previous techniques such as high computational cost and the need for manual configuration of the number of free parameters allocated to each layer. We evaluate the performance of dynamic reallocation methods in training deep convolutional networks and show that our method outperforms previous static and dynamic reparameterization methods, yielding the best accuracy for a fixed parameter budget, on par with accuracies obtained by iteratively pruning a pre-trained dense model. We further investigated the mechanisms underlying the superior generalization performance of the resultant sparse networks. We found that neither the structure, nor the initialization of the non-zero parameters were sufficient to explain the superior performance. Rather, effective learning crucially depended on the continuous exploration of the sparse network structure space during training. Our work suggests that exploring structural degrees of freedom during training is more effective than adding extra parameters to the network. Read More
Does Object Recognition Work for Everyone?
The paper analyzes the accuracy of publicly available object-recognition systems on a geographically diverse dataset. This dataset contains household items and was designed to have a more representative geographical coverage than commonly used image datasets in object recognition. We find that the systems perform relatively poorly on household items that commonly occur in countries with a low household income. Qualitative analyses suggest the drop in performance is primarily due to appearance differences within an object class (e.g., dish soap) and due to items appearing in a different context (e.g., toothbrushes appearing outside of bathrooms). The results of our study suggest that further work is needed to make object-recognition systems work equally well for people across different countries and income levels. Read More
Watching AI Slowly Forget a Human Face Is Incredibly Creepy
A programmer created an algorithmically-generated face, and then made the network slowly forget what its own face looked like.
The result, a piece of video art titled “What I saw before the darkness,” is an eerie time-lapse view of the inside of a demented AI’s mind as its artificial neurons are switched off, one by one, HAL 9000 style. Read More
Will China win the military AI race on the back of commercial technology?
The earliest weapons were dual-use technologies: rocks chipped into sharp edges and bound to arrows or spears or clubs that proved as useful for hunting as they did fighting.
Modern life is millennia removed from proto-ethical debates over the dangers of collaborating on hunting technology with people who may someday turn it to violence, but dual-use tools are at the center of a major inter- and intra-national debate. The U.S.-China Economic and Security Review Commission held a hearing June 7 about China and technology, specifically the ways in which developments in the civilian sector could be exploited and weaponized by China’s military.
“China has been hyped as an AI superpower poised to overtake the U.S. in the strategic technology domain of AI,” said Jeffrey Ding, China lead for the Center for the Governance of AI, Future of Humanity Institute, University of Oxford; D.Phil. Candidate, University of Oxford. Read More
Rick's Cafe AI 